© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58426
    Prev
    Next
    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash

    titles of movies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects superlative or comparative qualifiers in questions (e.g. “most,” “best,” “easiest,” “recently,” etc.).

    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
     Gus
    -0.07
    passes
    -0.07
     Ending
    -0.07
     Black
    -0.07
    width
    -0.06
     Guns
    -0.06
    wives
    -0.06
    atis
    -0.06
    value
    -0.06
    closed
    -0.06
    POSITIVE LOGITS
     naz
    0.07
    WindowSize
    0.06
    _presence
    0.06
     multim
    0.06
    !!↵↵
    0.06
    (units
    0.06
     ::↵
    0.06
    Div
    0.06
     ));↵↵
    0.06
     ย
    0.06
    Activations Density 0.045%

    No Known Activations