© 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. 39121
    Prev
    Next
    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash

    This neuron responds to the generic indefinite quantifier “any” (and similar generic “type”), marking broad or unspecific references.

    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
    setWidth
    -0.08
    let
    -0.07
     focal
    -0.07
     sulfate
    -0.07
     тол
    -0.07
     Miller
    -0.07
    excel
    -0.07
    _stamp
    -0.07
    school
    -0.07
    šel
    -0.07
    POSITIVE LOGITS
     any
    0.19
     Any
    0.16
    Any
    0.16
     ANY
    0.13
    any
    0.13
    -any
    0.11
    :Any
    0.11
    _ANY
    0.10
     Anthony
    0.10
    .Any
    0.09
    Activations Density 0.134%

    No Known Activations