© 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. 3-RESID-POST-AA
    11. 121830
    Prev
    Next
    INDEX
    Explanations

    op

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decline
    -0.07
     ول
    -0.07
     "=",
    -0.06
    _sessions
    -0.06
    %,
    -0.06
    koliv
    -0.06
    |--
    -0.06
     intermediate
    -0.06
     regulating
    -0.06
     DOMAIN
    -0.06
    POSITIVE LOGITS
     απο
    0.06
     rampant
    0.06
    /board
    0.06
    =email
    0.06
    -counter
    0.06
    ву
    0.06
    윤
    0.06
    宇
    0.06
    erture
    0.06
    Dave
    0.06
    Activations Density 0.003%

    No Known Activations