© 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. 92220
    Prev
    Next
    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of type‐variable names (e.g. single‐letter type parameters like s, u, m, p, etc.) in code.

    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
    _rooms
    -0.06
    แหล
    -0.06
     nữ
    -0.06
    /fonts
    -0.06
     basement
    -0.06
     увелич
    -0.06
     meltdown
    -0.06
    เกษ
    -0.06
     sotto
    -0.06
     πρέπει
    -0.06
    POSITIVE LOGITS
    د
    0.07
    eve
    0.07
     proud
    0.07
     &$
    0.06
     sightings
    0.06
     informational
    0.06
    (items
    0.06
     thêm
    0.06
    ÅŸ
    0.06
    ')['
    0.06
    Activations Density 0.008%

    No Known Activations