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. 84491
    Prev
    Next
    INDEX
    Explanations

    Calculate

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting the key words and structure of “remainder” (modulus) questions—i.e. the phrase “what is the remainder when … is divided by ….”

    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
    acr
    -0.06
     fence
    -0.06
     bliss
    -0.06
     ελλην
    -0.06
    approved
    -0.06
    판
    -0.06
    kind
    -0.06
    onn
    -0.06
    yt
    -0.06
     xử
    -0.06
    POSITIVE LOGITS
     ++)↵
    0.06
    (userName
    0.06
    (thing
    0.06
    ;m
    0.06
    /vector
    0.06
     bleiben
    0.06
     fuller
    0.06
    ifest
    0.06
    idata
    0.06
     rozhodnutí
    0.06
    Activations Density 0.019%

    No Known Activations