Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 26401
    Prev
    Next
    INDEX
    Explanations

    must

    np_max-act · gemini-2.0-flash

    terms related to software licensing and copyright notices.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects occurrences of the word “Redistributions” (as in the license header bullet point “* Redistributions of source…”).

    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
    럴
    -0.07
    chers
    -0.07
     Coğraf
    -0.06
    аном
    -0.06
    ского
    -0.06
    osit
    -0.06
    ому
    -0.06
    ///////////////////////////////////////////////////////////////////////////////↵
    -0.06
    structions
    -0.06
    ograph
    -0.06
    POSITIVE LOGITS
     teased
    0.06
     Must
    0.06
    _Format
    0.06
    ýn
    0.06
    .wait
    0.06
    MapView
    0.06
    .try
    0.06
    <Card
    0.06
    _TW
    0.06
     upscale
    0.06
    Activations Density 0.000%

    No Known Activations