© 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. 11-RESID-POST-AA
    11. 79507
    Prev
    Next
    INDEX
    Explanations

    TCP

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Griffin
    -0.07
    rots
    -0.07
     argent
    -0.07
     lire
    -0.07
     Hornets
    -0.07
     hadde
    -0.06
    .end
    -0.06
     mould
    -0.06
    гал
    -0.06
    _ghost
    -0.06
    POSITIVE LOGITS
     TCP
    0.15
    TCP
    0.12
     tcp
    0.11
    Tcp
    0.10
    _TCP
    0.10
    tcp
    0.09
     Tcp
    0.08
    (tcp
    0.08
    _tcp
    0.08
    ู
    0.07
    Activations Density 0.003%

    No Known Activations