© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58599
    Prev
    Next
    INDEX
    Explanations

    ated

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of voltage-gated ion channels (e.g. occurrences of “voltage-gated,” “gated,” and related channel-gating terms).

    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
     hug
    -0.06
    について
    -0.06
     swaps
    -0.06
     Dank
    -0.06
     annunci
    -0.06
    كل
    -0.06
    \uD
    -0.06
     Pref
    -0.06
    ็นพ
    -0.06
    ━━━━
    -0.06
    POSITIVE LOGITS
    emplo
    0.07
    usive
    0.07
    ,dim
    0.07
    /start
    0.07
    lider
    0.07
    agit
    0.06
    SELL
    0.06
    課
    0.06
    -pages
    0.06
    woo
    0.06
    Activations Density 0.003%

    No Known Activations