© 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. 7611
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on special dialogue‐structure tokens (speaker or header markers), i.e. it identifies the “assistant”/“user” header tags rather than content words.

    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
    内容
    -0.07
    _Target
    -0.07
    [A
    -0.06
    (Dictionary
    -0.06
     sabot
    -0.06
     considers
    -0.06
    .rotation
    -0.06
     Maxwell
    -0.06
     příprav
    -0.06
    %i
    -0.06
    POSITIVE LOGITS
    httpClient
    0.07
    uppen
    0.07
     constituent
    0.06
     Lt
    0.06
    editing
    0.06
    _ENABLE
    0.06
    ayın
    0.06
    larg
    0.06
     expose
    0.06
    nu
    0.06
    Activations Density 0.060%

    No Known Activations