© 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. 15-RESID-POST-AA
    11. 40064
    Prev
    Next
    INDEX
    Explanations

    Racing/Drivers with numbers

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Detect
    -0.07
     Vin
    -0.07
     Divider
    -0.07
     puff
    -0.06
     яс
    -0.06
     managing
    -0.06
     Dé
    -0.06
     Alic
    -0.06
    셜
    -0.06
    Ball
    -0.06
    POSITIVE LOGITS
    _AURA
    0.07
     olmasına
    0.06
    炉
    0.06
    .merge
    0.06
    tensorflow
    0.06
    INGS
    0.06
    ὶ
    0.06
    702
    0.06
    ;"
    0.06
    ές
    0.06
    Activations Density 0.043%

    No Known Activations