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. 99422
    Prev
    Next
    INDEX
    Explanations

    #define

    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
    VEC
    -0.06
    but
    -0.06
     autre
    -0.06
     snowy
    -0.06
    JI
    -0.06
    ็น
    -0.05
     خص
    -0.05
     alo
    -0.05
    ち
    -0.05
    ourt
    -0.05
    POSITIVE LOGITS
    \Configuration
    0.07
    ToBounds
    0.07
     případech
    0.06
    ueling
    0.06
     ','.
    0.06
     doubles
    0.06
    -addon
    0.06
     UserController
    0.06
    yahoo
    0.06
     Assy
    0.06
    Activations Density 0.004%

    No Known Activations