© 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. 57582
    Prev
    Next
    INDEX
    Explanations

    completeness

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect references to testing or evaluation (e.g., “test,” “testing,” “end-to-end,” “site function”) in the text.

    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
     maternal
    -0.06
     swagger
    -0.06
     �
    -0.06
    README
    -0.06
     mundane
    -0.06
     Afterwards
    -0.06
     binary
    -0.06
    ">×</
    -0.06
    evenodd
    -0.06
     sanctioned
    -0.06
    POSITIVE LOGITS
     Prahy
    0.07
     устан
    0.07
     Shot
    0.07
    ़न
    0.07
     SEARCH
    0.07
     Reggie
    0.07
     complains
    0.06
    люча
    0.06
    Cal
    0.06
    ź
    0.06
    Activations Density 0.285%

    No Known Activations