© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92432
    Prev
    Next
    INDEX
    Explanations

    amount/concentration

    np_max-act · gemini-2.0-flash

    The neuron activates on numerical tokens and numeric expressions (e.g. digits, decimal numbers, percentages, and other measurement values).

    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
     Teeth
    -0.08
    linear
    -0.07
    _VERTEX
    -0.07
     집
    -0.07
     tensor
    -0.06
    ‌کند
    -0.06
    .Messages
    -0.06
    .Dial
    -0.06
    cancellationToken
    -0.06
     빠
    -0.06
    POSITIVE LOGITS
     gratuites
    0.08
     získat
    0.06
     billig
    0.06
     cez
    0.06
     antes
    0.06
     δεν
    0.06
    uele
    0.06
    Lbl
    0.06
     grub
    0.06
     Danny
    0.06
    Activations Density 0.038%

    No Known Activations