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. 90332
    Prev
    Next
    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash

    This neuron lights up on standalone, proverb‐ or quotation‐style sentences—i.e. text enclosed in quotation marks (philosophical maxims or named quotes).

    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
    _WORK
    -0.07
    ToString
    -0.07
     grains
    -0.06
     DIE
    -0.06
    게임
    -0.06
     dread
    -0.06
    ADF
    -0.06
    _Delete
    -0.06
     scanning
    -0.06
     emulation
    -0.06
    POSITIVE LOGITS
     aconte
    0.07
    inations
    0.06
    (inflater
    0.06
     hele
    0.06
    岩
    0.06
    FUL
    0.06
    Aug
    0.06
     MethodInfo
    0.06
     확실
    0.06
     Flying
    0.06
    Activations Density 0.037%

    No Known Activations