© 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. 128764
    Prev
    Next
    INDEX
    Explanations

    Gibberish

    np_max-act · gemini-2.0-flash

    The neuron detects ASCII‐art drawing characters (e.g. “_” and “\”) used to compose simple text‐based graphics.

    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
    eger
    -0.07
     Rosen
    -0.07
     Walters
    -0.07
    iders
    -0.07
     koje
    -0.07
    ันย
    -0.07
    ombine
    -0.07
    _outputs
    -0.07
     mart
    -0.07
    record
    -0.06
    POSITIVE LOGITS
    .SetValue
    0.07
    (math
    0.07
     Apr
    0.07
     Registr
    0.06
    //------------------------------------------------------------------------------↵
    0.06
     Theft
    0.06
     protocols
    0.06
    +-+-
    0.06
     Bool
    0.06
    (bool
    0.06
    Activations Density 0.015%

    No Known Activations