© 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. 825
    Prev
    Next
    INDEX
    Explanations

    Sports performance/gameplay

    np_max-act · gemini-2.0-flash

    The neuron activates on words describing recent performance trends (like “in-form,” “dip (in form),” “run,” “streak,” etc.).

    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
     　　 　
    -0.07
    Allocation
    -0.07
     JVM
    -0.07
     přist
    -0.06
     frags
    -0.06
    PRINTF
    -0.06
     �
    -0.06
     ανα
    -0.06
    _dynamic
    -0.06
    等
    -0.06
    POSITIVE LOGITS
    ritis
    0.07
    _runs
    0.06
    ))*
    0.06
    orra
    0.06
    _Bl
    0.06
     nevě
    0.06
    학
    0.06
     العالمية
    0.06
     rested
    0.06
    ujet
    0.05
    Activations Density 0.018%

    No Known Activations