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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 85088
    Prev
    Next
    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numeric tokens—especially dates and year‐or day‐numbers—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information related to educational institutions and their characteristics.

    oai_token-act-pair · gpt-4o-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
     Commod
    -0.06
    income
    -0.06
     driven
    -0.06
    -country
    -0.06
    MAP
    -0.06
    combination
    -0.06
    humidity
    -0.06
     mamma
    -0.06
    Martin
    -0.06
     lat
    -0.06
    POSITIVE LOGITS
     ndarray
    0.07
    .AutoScaleDimensions
    0.07
     시행
    0.07
    ρίς
    0.06
     Isis
    0.06
     JQuery
    0.06
    chet
    0.06
    REDIT
    0.06
    ruits
    0.06
     ヴ
    0.06
    Activations Density 0.047%

    No Known Activations