© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 103182
    Prev
    Next
    INDEX
    Explanations

    sex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flattering
    -0.07
     fragrance
    -0.07
    constraint
    -0.07
     Π
    -0.06
    Fat
    -0.06
    State
    -0.06
     respective
    -0.06
     visibly
    -0.06
    	with
    -0.06
     clip
    -0.06
    POSITIVE LOGITS
    itar
    0.07
    gressive
    0.07
    ALLEL
    0.07
     useHistory
    0.06
    (password
    0.06
     urlencode
    0.06
     مبانی
    0.06
    :req
    0.06
    ㅠㅠ
    0.06
    ős
    0.06
    Activations Density 0.027%

    No Known Activations