© 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. 58185
    Prev
    Next
    INDEX
    Explanations

    followed

    np_max-act · gemini-2.0-flash

    The neuron responds to adverbs that describe gradual or step-by-step progression (e.g. “gradually”).

    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
    .apache
    -0.06
     Flower
    -0.06
     cellar
    -0.06
    �
    -0.06
     newPath
    -0.06
     Homes
    -0.06
    /popper
    -0.06
    .purchase
    -0.06
    _ad
    -0.06
    _UNSUPPORTED
    -0.06
    POSITIVE LOGITS
    Leod
    0.06
    America
    0.06
    uento
    0.06
    -rel
    0.06
     न
    0.06
     entren
    0.06
    uds
    0.06
    resas
    0.06
    openh
    0.06
     Penguin
    0.06
    Activations Density 0.035%

    No Known Activations