© 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. 15-RESID-POST-AA
    6. 91816
    Prev
    Next
    INDEX
    Explanations

    -

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    を持
    -0.07
     Operand
    -0.07
    (TreeNode
    -0.07
    .findById
    -0.07
    (dtype
    -0.06
     organism
    -0.06
    isEqualTo
    -0.06
     Widgets
    -0.06
     sağlayan
    -0.06
    _nn
    -0.06
    POSITIVE LOGITS
    HEIGHT
    0.06
     args
    0.06
     rifle
    0.06
    _horizontal
    0.06
     jewelry
    0.06
     فو
    0.06
    udoku
    0.06
     ':'
    0.06
     acct
    0.06
     неб
    0.06
    Activations Density 0.000%

    No Known Activations