© 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. 65879
    Prev
    Next
    INDEX
    Explanations

    Fermi Gamma-ray Space Telescope

    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
    _was
    -0.07
    جان
    -0.07
    东
    -0.06
    Lead
    -0.06
    _agg
    -0.06
    (itr
    -0.06
    dir
    -0.06
     используется
    -0.06
    宗
    -0.06
     ern
    -0.06
    POSITIVE LOGITS
    sgiving
    0.06
    aire
    0.06
     Registr
    0.06
     findAll
    0.06
    Named
    0.06
     Sessions
    0.06
     vacancy
    0.06
    izm
    0.06
    ôm
    0.06
    ьют
    0.06
    Activations Density 0.003%

    No Known Activations