© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 97951
    Prev
    Next
    INDEX
    Explanations

    ory

    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
     USING
    -0.07
     preacher
    -0.07
     الهند
    -0.07
     Rousse
    -0.07
    son
    -0.06
     Scan
    -0.06
    Allen
    -0.06
     Huffman
    -0.06
     considered
    -0.06
    .desc
    -0.06
    POSITIVE LOGITS
     victory
    0.16
     Victory
    0.13
     victories
    0.12
     triumph
    0.09
     victorious
    0.08
    ictory
    0.08
     trium
    0.08
    擊
    0.07
    uty
    0.07
     vict
    0.07
    Activations Density 0.006%

    No Known Activations