© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8933
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens and numerical expressions (e.g., digits, decimal 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
    prepared
    -0.06
    .Body
    -0.06
     valid
    -0.06
     Wikispecies
    -0.06
     lud
    -0.06
    .Toolbar
    -0.06
     em
    -0.06
    .der
    -0.06
    Containers
    -0.06
     deren
    -0.06
    POSITIVE LOGITS
    cháze
    0.06
     Eh
    0.06
    _vals
    0.06
    政治
    0.06
    ())↵
    0.06
     Sunderland
    0.06
     Billing
    0.06
    気持ち
    0.06
    (Set
    0.06
     özelliği
    0.06
    Activations Density 0.025%

    No Known Activations