© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42971
    Prev
    Next
    INDEX
    Explanations

    persisted

    np_max-act · gemini-2.0-flash

    The neuron fires on the formal, highly structured vocabulary and tokens of academic‐style writing—section headings, numbered lists, and technical terms—marking passages that read like a scholarly paper.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    negative perceptions of light-heartedness and compare them to the praise of serious themes in media.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     KBS
    -0.06
     quelle
    -0.06
    abant
    -0.06
    _IDX
    -0.06
    Medical
    -0.06
     acción
    -0.06
     mRNA
    -0.06
     Attorney
    -0.06
    ＼＼
    -0.06
    _Not
    -0.06
    POSITIVE LOGITS
    }));↵
    0.07
    Fragment
    0.07
    ProgressDialog
    0.07
    (wx
    0.07
     )),↵
    0.06
     participation
    0.06
    드는
    0.06
    .callback
    0.06
    _bm
    0.06
    ｱ
    0.06
    Activations Density 0.553%

    No Known Activations