© 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. 3-RESID-POST-AA
    6. 123034
    Prev
    Next
    INDEX
    Explanations

    two

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -bedroom
    -0.06
    wild
    -0.06
     Maybe
    -0.06
     expect
    -0.06
     etkil
    -0.06
    .backgroundColor
    -0.06
     Вик
    -0.06
     regexp
    -0.06
     Lightning
    -0.06
     Charm
    -0.06
    POSITIVE LOGITS
    Two
    0.18
     Two
    0.17
    Three
    0.10
     Three
    0.08
     TWO
    0.08
     döneminde
    0.08
     twin
    0.07
    two
    0.06
     Four
    0.06
     Adrian
    0.06
    Activations Density 0.030%

    No Known Activations