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. 19-RESID-POST-AA
    6. 52433
    Prev
    Next
    INDEX
    Explanations

    pregnancy

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cyan
    -0.07
    -fold
    -0.07
    ентов
    -0.06
    Inspect
    -0.06
     elsewhere
    -0.06
     redhead
    -0.06
     alb
    -0.06
    angling
    -0.06
     valve
    -0.06
    zman
    -0.06
    POSITIVE LOGITS
     @"";↵
    0.07
     Minimal
    0.06
    eus
    0.06
    contenido
    0.06
     Graphic
    0.06
     tol
    0.06
     Whats
    0.06
    ately
    0.06
    (predictions
    0.06
     Киє
    0.06
    Activations Density 0.060%

    No Known Activations