Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 10745
    Prev
    Next
    INDEX
    Explanations

    forced labor

    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
    /disable
    -0.07
    God
    -0.07
     clandest
    -0.07
    Relative
    -0.07
     Copper
    -0.07
    ircuit
    -0.06
     pancreatic
    -0.06
    360
    -0.06
     circuit
    -0.06
    signup
    -0.06
    POSITIVE LOGITS
     пы
    0.07
    .compile
    0.06
    围
    0.06
     Hồng
    0.06
     PUT
    0.06
    BUTTONDOWN
    0.06
    (valor
    0.06
     ``(
    0.06
    ([\
    0.06
    ADX
    0.06
    Activations Density 0.090%

    No Known Activations