© 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
    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. 54425
    Prev
    Next
    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash

    scenarios and contexts involving role-playing games.

    oai_token-act-pair · gpt-4oTriggered by @tcai

    The neuron is a detector for the token “play” (as used in role-play or “play” requests).

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

    dynamics of sibling relationships involving affection or romantic feelings.

    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
     thighs
    -0.06
     connections
    -0.06
    .Registry
    -0.06
     Blend
    -0.06
     consumed
    -0.06
    /console
    -0.06
     End
    -0.06
     changed
    -0.06
     end
    -0.06
     Syn
    -0.06
    POSITIVE LOGITS
    _rx
    0.08
     duel
    0.07
    韩
    0.07
    POP
    0.07
    (chan
    0.07
    тый
    0.07
    []>(
    0.07
    ая
    0.07
    ovatel
    0.06
     May
    0.06
    Activations Density 0.006%

    No Known Activations