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. 84723
    Prev
    Next
    INDEX
    Explanations

    cancer research papers

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurements or statistics, specifically floating‐point numbers (e.g. “0.348388671875,” “1.298828125,” 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
    keyCode
    -0.07
    loader
    -0.07
    accumulator
    -0.06
     GPU
    -0.06
    ギ
    -0.06
    pointer
    -0.06
     Wolverine
    -0.06
    _AST
    -0.06
    赢
    -0.06
     miscellaneous
    -0.06
    POSITIVE LOGITS
    ethylene
    0.07
     。
    0.06
     IoT
    0.06
     někdo
    0.06
     nivel
    0.06
    (!_
    0.06
     日本
    0.06
     пит
    0.06
     Projekt
    0.06
    preview
    0.06
    Activations Density 0.040%

    No Known Activations