© 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. 40394
    Prev
    Next
    INDEX
    Explanations

    ol

    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
     lesbian
    -0.07
    Never
    -0.07
     dubbed
    -0.06
    lices
    -0.06
     Dias
    -0.06
    .SplitContainer
    -0.06
    lere
    -0.06
     движ
    -0.06
     disparate
    -0.06
     getY
    -0.06
    POSITIVE LOGITS
    ol
    0.14
    OL
    0.12
    ols
    0.09
    ол
    0.08
     Vol
    0.08
    mol
    0.07
    Carol
    0.07
     Kol
    0.07
    Vol
    0.07
     Carol
    0.07
    Activations Density 0.090%

    No Known Activations