© 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. 42727
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens that are part of “Name_X and Name_Y” pairs—that is, it detects donor names joined by “and” in the list.

    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
     science
    -0.06
    λον
    -0.06
    字
    -0.06
    -column
    -0.06
    ρη
    -0.06
     степени
    -0.06
    KD
    -0.06
     Investors
    -0.06
    ,**
    -0.06
     Literature
    -0.06
    POSITIVE LOGITS
     рядом
    0.07
    $txt
    0.06
    jekt
    0.06
    chop
    0.06
    Marsh
    0.06
     الام
    0.06
     chuẩn
    0.06
     jedem
    0.06
     forn
    0.06
     garage
    0.06
    Activations Density 0.011%

    No Known Activations