© 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. 91529
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—counts, probabilities, or other numbers—i.e. it detects digits and numeric values in the text.

    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
     Represents
    -0.07
     repent
    -0.06
     організації
    -0.06
    -expand
    -0.06
     Kes
    -0.06
    .getvalue
    -0.06
     té
    -0.06
     zipfile
    -0.06
    _since
    -0.06
    -opacity
    -0.06
    POSITIVE LOGITS
     Nichols
    0.07
    _readable
    0.06
    -IS
    0.06
    UREMENT
    0.06
    分别
    0.06
    CAD
    0.06
     enhancement
    0.06
     improvements
    0.06
     Computers
    0.06
     schooling
    0.06
    Activations Density 0.001%

    No Known Activations