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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 83523
    Prev
    Next
    INDEX
    Explanations

    we

    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
    	mem
    -0.06
     бур
    -0.06
     sensors
    -0.06
    Div
    -0.06
    -alt
    -0.06
    .books
    -0.06
    ridor
    -0.06
    IBLE
    -0.06
     INSERT
    -0.06
     Cert
    -0.06
    POSITIVE LOGITS
    ']);
    ↵
    0.07
    เพลง
    0.07
     dwarf
    0.06
    ponsored
    0.06
     […]...↵
    0.06
    :a
    0.06
     nationalist
    0.06
    Celebr
    0.06
     […]↵
    0.06
     zh
    0.06
    Activations Density 0.193%

    No Known Activations