© 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. 126366
    Prev
    Next
    INDEX
    Explanations

    wise

    np_max-act · gemini-2.0-flash

    This neuron detects adverbs or modifiers ending in “‐wise” (e.g., row‐wise, block‐wise, pairwise, time‐wise).

    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
     endDate
    -0.08
     surpr
    -0.08
    {\"
    -0.07
     Lam
    -0.07
    -0.07
    ad
    -0.07
    <|end_of_text|>
    -0.07
    Metal
    -0.07
    \D
    -0.07
    AC
    -0.06
    POSITIVE LOGITS
    wise
    0.13
     wise
    0.11
    -wise
    0.11
     Wise
    0.10
    WISE
    0.10
     clockwise
    0.09
    wis
    0.09
    ise
    0.08
    wy
    0.08
     Grave
    0.08
    Activations Density 0.005%

    No Known Activations