© 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. 8002
    Prev
    Next
    INDEX
    Explanations

    save

    np_max-act · gemini-2.0-flash

    This neuron is tuned to detect mentions of relief‐pitching statistics—especially “save” counts and closer roles—in baseball coverage.

    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
     Triumph
    -0.07
     Empty
    -0.07
    üsü
    -0.07
    _metadata
    -0.06
    ogenerated
    -0.06
     awakeFromNib
    -0.06
     قم
    -0.06
    Mari
    -0.06
    聖
    -0.06
     Barry
    -0.06
    POSITIVE LOGITS
    .dump
    0.06
     """
↵
↵
    0.06
     购
    0.06
    resher
    0.06
     кис
    0.06
     Websites
    0.06
     """
↵
    0.06
     nouvelles
    0.06
     дог
    0.06
     área
    0.06
    Activations Density 0.001%

    No Known Activations