© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 53642
    Prev
    Next
    INDEX
    Explanations

    Time periods

    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
    장을
    -0.07
     deity
    -0.07
     Trustees
    -0.07
     kone
    -0.07
     ει
    -0.07
     federally
    -0.06
    ALES
    -0.06
     topology
    -0.06
     vibr
    -0.06
     Tribe
    -0.06
    POSITIVE LOGITS
     regards
    0.08
     separat
    0.07
     Usually
    0.06
    DST
    0.06
    Usually
    0.06
    Unless
    0.06
    ftar
    0.06
    :&
    0.06
    681
    0.06
     KC
    0.06
    Activations Density 0.023%

    No Known Activations