© 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. 57945
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects instances of “looking to” (i.e., expressions of intent or planned action).

    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
    "Yes
    -0.06
    .consume
    -0.06
     categorie
    -0.06
     boring
    -0.06
     fuck
    -0.06
     moderator
    -0.06
     granddaughter
    -0.06
    ("{\"
    -0.06
     الاج
    -0.06
     compagn
    -0.06
    POSITIVE LOGITS
    To
    0.09
    to
    0.08
     tipped
    0.07
    etur
    0.07
     To
    0.07
     Nghị
    0.07
    TO
    0.07
    TI
    0.07
    X
    0.07
    践
    0.07
    Activations Density 0.021%

    No Known Activations