© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68744
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    technical specifications and formatting related to programming libraries or software components.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is tuned to detect version‐style numeric strings (e.g. “2.3.2” or “11.2.2”).

    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
    예
    -0.07
    istributor
    -0.07
    --------------------------------------------------------------------------↵
    -0.06
    ,private
    -0.06
    610
    -0.06
     hated
    -0.06
    arket
    -0.06
     ));↵↵
    -0.06
    Incoming
    -0.06
    �장
    -0.06
    POSITIVE LOGITS
    /sites
    0.07
    kyně
    0.06
    alardan
    0.06
    /my
    0.06
    Median
    0.06
    جی
    0.06
    (Html
    0.06
    δης
    0.06
    /Instruction
    0.06
    내기
    0.06
    Activations Density 0.012%

    No Known Activations