© 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 EvalsExportsAPI 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. 57394
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash

    The neuron activates on statements in the assistant’s reasoning about whether a tool is required—i.e. tokens in its “Thought” reasoning indicating necessity or decision to utilize a tool.

    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
     seizure
    -0.06
    ATORS
    -0.06
     gays
    -0.06
    建設
    -0.06
    .proj
    -0.06
     Manafort
    -0.06
    ncmp
    -0.06
    Β
    -0.06
    Hour
    -0.06
    ・━・━・━・━
    -0.06
    POSITIVE LOGITS
    보다
    0.07
    -return
    0.07
    Live
    0.06
    /trunk
    0.06
    ivariate
    0.06
    StateChanged
    0.06
     vời
    0.06
    resentation
    0.06
    VERTEX
    0.06
     different
    0.06
    Activations Density 0.008%

    No Known Activations