Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6659
    Prev
    Next
    INDEX
    Explanations

    Sports stories

    np_max-act · gemini-2.0-flash

    elements of competitive sporting events and highlight key moments or performances.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is detect descriptions of scoring or goal‐related actions (verbs and phrases) in sports play‐by‐play commentary.

    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
     classify
    -0.07
    Filters
    -0.06
    för
    -0.06
    Plug
    -0.06
     Lowest
    -0.06
    <link
    -0.06
    Mathf
    -0.06
    idget
    -0.06
    _Default
    -0.06
    HN
    -0.06
    POSITIVE LOGITS
     teg
    0.07
     w
    0.06
     dun
    0.06
    *pi
    0.06
     zahrn
    0.06
    [test
    0.06
    ovně
    0.06
    andır
    0.06
    диви
    0.06
     didReceiveMemoryWarning
    0.06
    Activations Density 0.011%

    No Known Activations