© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126205
    Prev
    Next
    INDEX
    Explanations

    Android code

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric tokens (digits), especially measurements or IDs containing numbers.

    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
     всё
    -0.07
     murky
    -0.06
     dividing
    -0.06
     celebrity
    -0.06
    /inet
    -0.06
    щий
    -0.06
    vertex
    -0.06
     furry
    -0.06
     skull
    -0.06
     dubious
    -0.06
    POSITIVE LOGITS
     warmly
    0.07
    \F
    0.07
    ização
    0.06
    emma
    0.06
    .assertIs
    0.06
     상세
    0.06
    mond
    0.06
    quisa
    0.06
    Ze
    0.06
     أكتوبر
    0.06
    Activations Density 0.032%

    No Known Activations