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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29819
    Prev
    Next
    INDEX
    Explanations

    Forum prompts/challenges

    np_max-act · gemini-2.0-flash

    This neuron detects phrasing that asks for travel recommendations—words like “suggest,” “place,” “visit,” and “near” in requests for places to visit.

    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
    gent
    -0.07
    (v
    -0.07
    san
    -0.07
    -0.06
     Gallup
    -0.06
    ople
    -0.06
    -location
    -0.06
    OV
    -0.06
    Side
    -0.06
     Pawn
    -0.06
    POSITIVE LOGITS
     وغير
    0.06
     στα
    0.06
    ")->
    0.06
    ุบ
    0.06
    ="'.$
    0.06
     ESPN
    0.06
     코로나
    0.06
    �
    0.06
    .UNRELATED
    0.06
    .gsub
    0.06
    Activations Density 0.067%

    No Known Activations