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. 130486
    Prev
    Next
    INDEX
    Explanations

    pancakes

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot mentions of specific food or dish names (e.g., menu items).

    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
    )'],↵
    -0.07
     škol
    -0.07
     Root
    -0.07
     Proposed
    -0.06
     Михай
    -0.06
     carg
    -0.06
    ---@
    -0.06
     celestial
    -0.06
    597
    -0.06
     joined
    -0.06
    POSITIVE LOGITS
     남자
    0.07
    NDER
    0.06
     hacker
    0.06
     scanner
    0.06
     Goat
    0.06
     Scanner
    0.06
    わず
    0.06
    れば
    0.06
     maternity
    0.06
    UserCode
    0.06
    Activations Density 0.009%

    No Known Activations