© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54036
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase “based on publicly available information” (references to sourcing information as publicly available).

    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
    .Mail
    -0.07
     meetings
    -0.06
    _SELECTION
    -0.06
    tribution
    -0.06
    Các
    -0.06
     Các
    -0.06
    获
    -0.06
    _traffic
    -0.06
    /comment
    -0.06
    ΜΑΤ
    -0.06
    POSITIVE LOGITS
    _iff
    0.07
    _rand
    0.07
     Increased
    0.06
     extravag
    0.06
    翻
    0.06
    (ur
    0.06
    	matrix
    0.06
    iza
    0.06
    _Destroy
    0.06
    "testing
    0.06
    Activations Density 0.043%

    No Known Activations