© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128837
    Prev
    Next
    INDEX
    Explanations

    shot

    np_max-act · gemini-2.0-flash

    The neuron activates on in-match soccer play-by-play language—especially references to the ball being passed, shot, crossed, or driven toward goal.

    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
    sid
    -0.07
    amat
    -0.06
     snaps
    -0.06
    UMENT
    -0.06
     roaming
    -0.06
    .St
    -0.06
     WA
    -0.06
     Commission
    -0.06
     motivating
    -0.06
     Angle
    -0.06
    POSITIVE LOGITS
     окрем
    0.07
    /she
    0.07
     Others
    0.06
    ublice
    0.06
     Prostit
    0.06
    ilitary
    0.06
    hf
    0.06
    ripper
    0.06
     پرو
    0.06
    شو
    0.06
    Activations Density 0.005%

    No Known Activations