© 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. 814
    Prev
    Next
    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on mentions of the mother (e.g. “mom,” “her mother”) and related referential 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
     barrel
    -0.08
    san
    -0.07
    iare
    -0.07
    fv
    -0.06
    Initially
    -0.06
    connexion
    -0.06
     descended
    -0.06
    乳
    -0.06
     cigars
    -0.06
     pool
    -0.06
    POSITIVE LOGITS
     capita
    0.06
    误
    0.06
     repost
    0.06
     Giới
    0.06
     váž
    0.06
            	↵
    0.06
    _ori
    0.06
    .splitContainer
    0.06
     conforme
    0.06
     beware
    0.06
    Activations Density 0.015%

    No Known Activations