© 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. 43457
    Prev
    Next
    INDEX
    Explanations

    book reviews and accounts

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of historical authenticity or accuracy—i.e. references to fact vs. fiction, “true,” “historical,” “mythic,” and related terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     bus
    -0.07
    ely
    -0.07
     rij
    -0.07
     chaud
    -0.06
    gart
    -0.06
    ouz
    -0.06
    ulis
    -0.06
    undi
    -0.06
     onTap
    -0.06
    .InputStream
    -0.06
    POSITIVE LOGITS
     autoimmune
    0.07
    �
    0.07
    _GO
    0.07
    …↵↵
    0.07
     REPL
    0.07
    ุบาล
    0.07
     $($
    0.06
    errated
    0.06
    ┣
    0.06
    �
    0.06
    Activations Density 0.061%

    No Known Activations