© 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 EvalsExportsAPI 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. 38811
    Prev
    Next
    INDEX
    Explanations

    frame

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases related to inserting or setting keyframes and animating properties (e.g. “keyframe,” “frame,” “animate,” “timeline,” “set”).

    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
     수도
    -0.06
     Collins
    -0.06
    _D
    -0.06
    to
    -0.06
     DAL
    -0.06
     ها
    -0.06
    .IO
    -0.06
    _ro
    -0.05
    ()){↵
    -0.05
    Telefono
    -0.05
    POSITIVE LOGITS
     سبز
    0.08
    ncias
    0.07
    限制
    0.07
     immortal
    0.07
     Median
    0.07
     Ub
    0.06
     drifted
    0.06
    εργ
    0.06
    _lookup
    0.06
    Point
    0.06
    Activations Density 0.008%

    No Known Activations