© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 35693
    Prev
    Next
    INDEX
    Explanations

    code and identification numbers

    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
     arasında
    -0.06
     hospitalized
    -0.06
     neboť
    -0.06
     запрос
    -0.06
    VIC
    -0.06
    labilir
    -0.06
    ittest
    -0.06
    Excel
    -0.06
    (tc
    -0.06
     welche
    -0.06
    POSITIVE LOGITS
    danger
    0.07
     avait
    0.06
    birds
    0.06
    _MIN
    0.06
    continuous
    0.06
     mListener
    0.06
    .borrow
    0.06
    無料
    0.06
    .capacity
    0.06
    ceptive
    0.06
    Activations Density 0.072%

    No Known Activations