© 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. 3-RESID-POST-AA
    11. 121781
    Prev
    Next
    INDEX
    Explanations

    soccer/football

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shine
    -0.07
    吸
    -0.07
    τια
    -0.06
    _lists
    -0.06
    346
    -0.06
     Dank
    -0.06
    itated
    -0.06
    471
    -0.06
    -guide
    -0.06
    hh
    -0.06
    POSITIVE LOGITS
     cumpl
    0.21
     UEFA
    0.17
     Waterloo
    0.15
     Pont
    0.11
     Renault
    0.11
     επι
    0.09
     Pé
    0.08
    Pont
    0.08
     Napoleon
    0.07
     Ки
    0.06
    Activations Density 0.002%

    No Known Activations