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. 129057
    Prev
    Next
    INDEX
    Explanations

    helper verbs

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numeric literals (decimal numbers) in source 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
     relocation
    -0.06
     timestamp
    -0.06
     Kore
    -0.06
    90
    -0.06
    (body
    -0.06
     Hank
    -0.06
    reen
    -0.06
    Jones
    -0.06
    BJ
    -0.06
     buildup
    -0.06
    POSITIVE LOGITS
     initData
    0.07
    >
    ↵
    ↵
    ↵
    0.06
    Cities
    0.06
     Planner
    0.06
     zbo
    0.06
     sạch
    0.06
    *******************************************************************************/↵
    0.06
     numel
    0.06
    のが
    0.06
     Viet
    0.06
    Activations Density 0.031%

    No Known Activations