© 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
    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. 84647
    Prev
    Next
    INDEX
    Explanations

    period

    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
    irector
    -0.07
     firefighter
    -0.07
     RD
    -0.06
    )는
    -0.06
     driv
    -0.06
     Prof
    -0.06
     rode
    -0.06
     datasource
    -0.06
     actor
    -0.06
     LU
    -0.06
    POSITIVE LOGITS
     मध
    0.07
     حدود
    0.07
     nguyện
    0.07
    ToLower
    0.06
     터
    0.06
    Türkiye
    0.06
    ‌رس
    0.06
    (animated
    0.06
    (verbose
    0.06
     FITNESS
    0.06
    Activations Density 0.099%

    No Known Activations