© 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. 58373
    Prev
    Next
    INDEX
    Explanations

    IST eval

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of formal clinical‐trial criteria or response evaluation guidelines (e.g. “measurable disease,” “RECIST,” inclusion/exclusion rules”).

    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
     operated
    -0.06
    (port
    -0.06
    (_)
    -0.06
    _testing
    -0.06
     arrang
    -0.06
    (nn
    -0.06
    castle
    -0.06
    .ff
    -0.06
     lept
    -0.06
    .trip
    -0.06
    POSITIVE LOGITS
    240
    0.07
    _HIDDEN
    0.07
    getObject
    0.06
     quil
    0.06
     새글
    0.06
     timeframe
    0.06
     Soldiers
    0.06
    /*@
    0.06
     orbs
    0.06
    								↵
    0.06
    Activations Density 0.004%

    No Known Activations