© 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. 7837
    Prev
    Next
    INDEX
    Explanations

    dialogue snippets

    np_max-act · gemini-2.0-flash

    This neuron lights up on the explicit “Yes”/“No” answer tokens, i.e. it detects the words “Yes” or “No.”

    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
     yas
    -0.07
    istorical
    -0.07
    ling
    -0.07
     ministers
    -0.07
    whose
    -0.06
    .get
    -0.06
     billions
    -0.06
    -blood
    -0.06
    цу
    -0.06
    -produced
    -0.06
    POSITIVE LOGITS
     BELOW
    0.07
     VERBOSE
    0.06
     ό
    0.06
     contraceptive
    0.06
    =k
    0.06
     Edited
    0.06
    stringLiteral
    0.06
     dumpsters
    0.06
     trest
    0.06
     crem
    0.06
    Activations Density 0.016%

    No Known Activations