© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109072
    Prev
    Next
    INDEX
    Explanations

    Code, migrations, dependencies

    np_max-act · gemini-2.0-flash

    This neuron detects assembler‐style directive tokens (e.g. lines beginning with “.end”, “.method”, “.field”, etc.) in compiled bytecode listings.

    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
    _references
    -0.07
     STILL
    -0.06
     estados
    -0.06
     Sources
    -0.06
    _player
    -0.06
     frustr
    -0.06
     namely
    -0.06
    Chapter
    -0.06
    Sources
    -0.06
     ihrer
    -0.06
    POSITIVE LOGITS
    елем
    0.07
    ewear
    0.07
    /con
    0.07
     doomed
    0.07
    pageIndex
    0.07
     єв
    0.07
    userid
    0.06
     зависит
    0.06
     �
    0.06
    NIEnv
    0.06
    Activations Density 0.003%

    No Known Activations