© 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 (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 9381
    Prev
    Next
    INDEX
    Explanations

    Conversational rambling

    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
     olduğuna
    -0.07
     pneumonia
    -0.06
    <tbody
    -0.06
    úp
    -0.06
     있다는
    -0.06
    为什么
    -0.06
     Пер
    -0.06
     ye
    -0.06
    Пер
    -0.06
    ♀♀♀♀
    -0.06
    POSITIVE LOGITS
     passionately
    0.07
    لق
    0.06
    ring
    0.06
     Dire
    0.06
     Strateg
    0.06
     weighting
    0.06
    374
    0.06
    .instrument
    0.06
     SMS
    0.06
    _disc
    0.06
    Activations Density 0.142%

    No Known Activations