© 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. 58591
    Prev
    Next
    INDEX
    Explanations

    anything

    np_max-act · gemini-2.0-flash

    This neuron responds to the filler phrase “anything else.”

    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
     sample
    -0.08
    scores
    -0.07
    _pose
    -0.07
    Level
    -0.07
     Level
    -0.06
     new
    -0.06
    StateMachine
    -0.06
     samples
    -0.06
     fö
    -0.06
     Example
    -0.06
    POSITIVE LOGITS
     anything
    0.17
     nothing
    0.14
    Anything
    0.13
    anything
    0.13
     Anything
    0.12
    nothing
    0.12
     everything
    0.12
     Nothing
    0.11
    Nothing
    0.11
     Everything
    0.11
    Activations Density 0.054%

    No Known Activations