© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126675
    Prev
    Next
    INDEX
    Explanations

    remote work

    np_max-act · gemini-2.0-flash

    The neuron identifies numbered list items and their associated content—i.e. it fires on tokens forming “1. …”, “2. …”, etc., and the words that follow them.

    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
    ПК
    -0.08
    .showMessage
    -0.07
     NGC
    -0.07
    />.
    -0.07
     Indicator
    -0.07
     구
    -0.07
     obligation
    -0.06
     дод
    -0.06
     impossible
    -0.06
    やす
    -0.06
    POSITIVE LOGITS
    .sp
    0.06
    (comm
    0.06
    /validation
    0.06
    queries
    0.06
    .BUTTON
    0.06
    ritt
    0.06
     dye
    0.06
    .Flush
    0.06
     заст
    0.06
     pourrait
    0.06
    Activations Density 0.024%

    No Known Activations