© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44171
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron is detecting numeric tokens (digits or numbers, often with decimals) that represent quantities.

    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
     меш
    -0.07
    _CHANGE
    -0.06
    .ma
    -0.06
     clergy
    -0.06
    _Title
    -0.06
    .machine
    -0.06
     Mae
    -0.06
    جو
    -0.06
    arLayout
    -0.06
    .Constraint
    -0.06
    POSITIVE LOGITS
     catching
    0.07
     „
    0.07
     khả
    0.06
    <\/
    0.06
    ,err
    0.06
    Quite
    0.06
    _OPT
    0.06
     더욱
    0.06
     COUNT
    0.06
     Become
    0.06
    Activations Density 0.024%

    No Known Activations