© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 701
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects contrastive discourse markers (e.g. “However,”) that introduce exceptions or contrasting statements.

    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
     Frage
    -0.07
     claws
    -0.06
    _prepare
    -0.06
    _values
    -0.06
     watch
    -0.06
     Pussy
    -0.06
     phép
    -0.06
    ens
    -0.06
    нии
    -0.06
     cider
    -0.06
    POSITIVE LOGITS
    //*[@
    0.08
    .platform
    0.07
     그리고
    0.07
    ivic
    0.07
    .xrLabel
    0.07
    าภ
    0.06
    #,
    0.06
    ertino
    0.06
     consulate
    0.06
    .HttpStatus
    0.06
    Activations Density 0.026%

    No Known Activations