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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74125
    Prev
    Next
    INDEX
    Explanations

    code file paths

    np_max-act · gemini-2.0-flash

    This neuron is sensitive to punctuation-heavy tokens, especially fragments of URLs, file paths, and version specifiers (slashes, colons, dots, and hyphens).

    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
    JNIEXPORT
    -0.08
    协
    -0.07
     algunos
    -0.06
     학
    -0.06
    _bio
    -0.06
    There
    -0.06
    روه
    -0.06
    GenericType
    -0.06
    asd
    -0.06
    chs
    -0.06
    POSITIVE LOGITS
     daytime
    0.06
    (sprite
    0.06
     Almighty
    0.06
     markedly
    0.06
     coli
    0.06
     Potter
    0.06
     خانواده
    0.06
     goalie
    0.06
    azes
    0.06
     wholesale
    0.06
    Activations Density 0.018%

    No Known Activations