Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 40637
    Prev
    Next
    INDEX
    Explanations

    Research/math text

    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
    36
    -0.07
    rollo
    -0.06
     radiation
    -0.06
    těl
    -0.06
    thest
    -0.06
    Integrated
    -0.06
    Glyph
    -0.06
    Segments
    -0.06
    рукту
    -0.06
     движения
    -0.06
    POSITIVE LOGITS
     render
    0.07
    _DR
    0.07
     inclus
    0.07
     passer
    0.07
     persists
    0.07
    alley
    0.07
     Xamarin
    0.07
     gente
    0.07
     CREATED
    0.07
    .easy
    0.06
    Activations Density 0.035%

    No Known Activations