© 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. 58546
    Prev
    Next
    INDEX
    Explanations

    Coding suggestions

    np_max-act · gemini-2.0-flash

    This neuron detects the “A:” answer marker at the start of the answer section.

    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
     Shipping
    -0.07
     temperatures
    -0.06
     Temperature
    -0.06
     sez
    -0.06
    정을
    -0.06
     før
    -0.06
     commissioners
    -0.06
    ูก
    -0.06
     fetish
    -0.06
     foregoing
    -0.06
    POSITIVE LOGITS
     základ
    0.08
    fffffff
    0.07
    [text
    0.07
    uluk
    0.06
    WindowTitle
    0.06
    》（
    0.06
    _AA
    0.06
     *,
    0.06
    ller
    0.06
    quoted
    0.06
    Activations Density 0.073%

    No Known Activations