Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 69092
    Prev
    Next
    INDEX
    Explanations

    growth

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing decimal (floating-point) 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
     پسر
    -0.07
    _icon
    -0.07
    Gallery
    -0.06
     sáng
    -0.06
    _recent
    -0.06
    classify
    -0.06
     messages
    -0.06
    ########################################################################
    -0.06
     ومن
    -0.06
    кувати
    -0.06
    POSITIVE LOGITS
     YY
    0.07
    Quiet
    0.06
    .hit
    0.06
    NonQuery
    0.06
     Sy
    0.06
    (FLAGS
    0.06
     su
    0.06
     unregister
    0.06
     these
    0.06
    慧
    0.06
    Activations Density 0.087%

    No Known Activations