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. 23-RESID-POST-AA
    6. 7563
    Prev
    Next
    INDEX
    Explanations

    GF

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erle
    -0.07
    xiv
    -0.07
    rst
    -0.06
    وی
    -0.06
    EW
    -0.06
    grese
    -0.06
    plings
    -0.06
    
    -0.06
     emojis
    -0.06
    elson
    -0.06
    POSITIVE LOGITS
     відповідаль
    0.07
     πραγμα
    0.07
    engineering
    0.07
    Concept
    0.07
     choisir
    0.07
     растений
    0.06
    -boot
    0.06
     injured
    0.06
     �
    0.06
    /company
    0.06
    Activations Density 0.002%

    No Known Activations