© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 99742
    Prev
    Next
    INDEX
    Explanations

    Day

    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
    anning
    -0.07
    Bu
    -0.07
     Γεν
    -0.07
     vulnerabilities
    -0.07
    Но
    -0.06
     prostřednictvím
    -0.06
    стров
    -0.06
     baik
    -0.06
     Є
    -0.06
     Bolton
    -0.06
    POSITIVE LOGITS
     Day
    0.07
     Girlfriend
    0.07
     DAY
    0.06
    igated
    0.06
    CHAPTER
    0.06
     vận
    0.06
    .RESET
    0.06
    645
    0.06
    Reserved
    0.06
    atial
    0.06
    Activations Density 0.023%

    No Known Activations