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. 42151
    Prev
    Next
    INDEX
    Explanations

    FIG

    np_max-act · gemini-2.0-flash

    The neuron responds to references to figures and their accompanying numbers (e.g. “FIG 1,” “FIG 2,” etc.).

    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
     слов
    -0.07
    ヶ
    -0.06
    _TRUE
    -0.06
     siè
    -0.06
     insurers
    -0.06
    _ATTACH
    -0.06
    skyt
    -0.06
    slt
    -0.06
    uyla
    -0.06
     preca
    -0.06
    POSITIVE LOGITS
     moduleName
    0.07
     développ
    0.07
    App
    0.06
     Woodward
    0.06
     straightforward
    0.06
     wagon
    0.06
     compensate
    0.06
    	Log
    0.06
    %X
    0.06
     ΑΠ
    0.06
    Activations Density 0.008%

    No Known Activations