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. 84976
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric literals (especially floating-point constants) in the code.

    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
    ,float
    -0.06
     checkboxes
    -0.06
     barric
    -0.06
     hashlib
    -0.06
     choices
    -0.06
     formats
    -0.06
     varios
    -0.06
    aların
    -0.06
    -aware
    -0.06
     fare
    -0.06
    POSITIVE LOGITS
    _EXTRA
    0.08
     genuinely
    0.06
    ubby
    0.06
     Schwe
    0.06
    ±
    0.06
     STOP
    0.06
    dum
    0.06
     دانلود
    0.06
    DL
    0.06
     STE
    0.06
    Activations Density 0.060%

    No Known Activations