© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126112
    Prev
    Next
    INDEX
    Explanations

    Biomechanics and kinesiology

    np_max-act · gemini-2.0-flash

    The neuron detects technical biomechanics and movement‐analysis terms (like kinematics, kinetics, gait, motion, translation).

    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
    .setRotation
    -0.07
    θος
    -0.07
     cites
    -0.07
    ail
    -0.06
    เบ
    -0.06
    olin
    -0.06
    .maven
    -0.06
     Animal
    -0.06
    actor
    -0.06
    ROUP
    -0.06
    POSITIVE LOGITS
     inducing
    0.07
    quality
    0.06
    ็็
    0.06
    ışık
    0.06
    ného
    0.06
    -product
    0.06
     Profession
    0.06
     ostream
    0.06
    pegawai
    0.06
    ,’”
    0.06
    Activations Density 0.031%

    No Known Activations