© 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. 92267
    Prev
    Next
    INDEX
    Explanations

    as

    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
     Hopefully
    -0.07
     isn
    -0.07
     suddenly
    -0.07
    entialAction
    -0.06
     regulation
    -0.06
     Silence
    -0.06
     Streets
    -0.06
     appears
    -0.06
     Abilities
    -0.06
     эта
    -0.06
    POSITIVE LOGITS
    deck
    0.06
     Marvel
    0.06
    @SuppressWarnings
    0.06
     dorm
    0.06
     حکم
    0.06
    ěž
    0.06
     Recorder
    0.06
    ๆ
    0.06
    java
    0.06
     retract
    0.06
    Activations Density 0.000%

    No Known Activations