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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58757
    Prev
    Next
    INDEX
    Explanations

    ](

    np_max-act · gemini-2.0-flash

    The neuron identifies in‐text citation markers and reference‐identifier tokens (e.g. numbered or tagged bibliography callouts).

    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
     circuit
    -0.07
     rencont
    -0.06
     misuse
    -0.06
     prostate
    -0.06
    aph
    -0.06
     Circuit
    -0.06
    том
    -0.06
    ffff
    -0.06
    opor
    -0.06
    asty
    -0.06
    POSITIVE LOGITS
     peníze
    0.06
     kao
    0.06
    .")↵
    0.06
     tu
    0.06
    /nav
    0.06
     Twitter
    0.06
     gọi
    0.06
     TRY
    0.06
     gre
    0.06
    ']↵↵↵
    0.06
    Activations Density 0.009%

    No Known Activations