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. 7-RESID-POST-AA
    6. 25289
    Prev
    Next
    INDEX
    Explanations

    enable/disable functions

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (points
    -0.07
     poles
    -0.07
     mult
    -0.06
     brains
    -0.06
     Woods
    -0.06
    克斯
    -0.06
    Gen
    -0.06
     Heaven
    -0.06
     Huyện
    -0.06
    cade
    -0.06
    POSITIVE LOGITS
     perpetrated
    0.07
    のだろう
    0.06
     Sab
    0.06
     जन
    0.06
     compliments
    0.06
     amour
    0.06
     тощо
    0.06
    latitude
    0.06
    550
    0.06
    لى
    0.06
    Activations Density 0.134%

    No Known Activations