© 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. 118077
    Prev
    Next
    INDEX
    Explanations

    Non-English

    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
    ilebilir
    -0.07
     uygun
    -0.07
     deline
    -0.06
    Leo
    -0.06
    rale
    -0.06
     rizik
    -0.06
     deton
    -0.06
     prive
    -0.06
     seafood
    -0.06
    .getEnd
    -0.06
    POSITIVE LOGITS
    本
    0.07
    're
    0.07
    $h
    0.07
    agan
    0.07
    (ins
    0.06
    _Osc
    0.06
    !=↵
    0.06
    AIN
    0.06
    _SHA
    0.06
    throat
    0.06
    Activations Density 0.002%

    No Known Activations