Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130228
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash

    The neuron fires on technical mentions of vehicle interior hardware—especially parts of a central console (storage compartments, lid modules, pivots, armrests, 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
    ;↵
    -0.06
     Tories
    -0.06
     Chains
    -0.06
     "";
    ↵
    ↵
    -0.06
     grape
    -0.06
     Annual
    -0.06
     ~~
    -0.06
    _miss
    -0.06
     getLocation
    -0.06
    >());↵
    -0.06
    POSITIVE LOGITS
    英語
    0.08
    -div
    0.07
    jas
    0.07
     configur
    0.07
    	finally
    0.07
     กร
    0.06
     cfg
    0.06
    /div
    0.06
     lush
    0.06
    (jsonObject
    0.06
    Activations Density 0.317%

    No Known Activations