© 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
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 35666
    Prev
    Next
    INDEX
    Explanations

    writing overwrite

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —it
    -0.08
    ]-
    -0.07
    ०
    -0.07
     Roose
    -0.07
     Rush
    -0.07
     fascism
    -0.07
    —if
    -0.06
     Rational
    -0.06
     Technician
    -0.06
    —the
    -0.06
    POSITIVE LOGITS
     반환
    0.07
    (TEXT
    0.07
     добре
    0.07
     overwritten
    0.06
    _HOR
    0.06
     unmist
    0.06
    _sparse
    0.06
     Cougar
    0.06
    lets
    0.06
     di
    0.06
    Activations Density 0.006%

    No Known Activations