© 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. 128870
    Prev
    Next
    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens marking the start of the assistant’s own reply—e.g. header identifiers and initial words (“I,” “It,” “The”) at the beginning of the assistant’s sentences.

    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
    CONS
    -0.07
    /boot
    -0.07
    _vocab
    -0.07
     Narrow
    -0.06
    vail
    -0.06
     footnote
    -0.06
     जग
    -0.06
     Semantic
    -0.06
     شمال
    -0.06
    averse
    -0.06
    POSITIVE LOGITS
    _low
    0.07
     seit
    0.07
    .BooleanField
    0.06
    äng
    0.06
     компании
    0.06
     patří
    0.06
     různých
    0.06
    алась
    0.06
    sortable
    0.06
    .multiply
    0.06
    Activations Density 0.118%

    No Known Activations