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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126307
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    The neuron is tuned to pick out longer, multi‐syllable technical or domain-specific terms (e.g. jargon and formal content words).

    oai_token-act-pair · o4-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
     있던
    -0.06
    :convert
    -0.06
    асс
    -0.06
    Apparently
    -0.06
    Dic
    -0.06
    ，被
    -0.06
     ит
    -0.06
     кирп
    -0.06
    (area
    -0.06
     Bass
    -0.06
    POSITIVE LOGITS
     invoke
    0.06
     vc
    0.06
    nement
    0.06
     Sovere
    0.06
    .sat
    0.06
    _fifo
    0.06
     railing
    0.06
     SIP
    0.06
     Appro
    0.06
    /st
    0.06
    Activations Density 0.055%

    No Known Activations