© 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. 7-RESID-POST-AA
    11. 35856
    Prev
    Next
    INDEX
    Explanations

    AppDelegate

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancers
    -0.08
    Benef
    -0.07
    νον
    -0.07
    urgery
    -0.06
     فرزند
    -0.06
    .DisplayName
    -0.06
    ρών
    -0.06
    Thông
    -0.06
     资
    -0.06
     strangers
    -0.06
    POSITIVE LOGITS
     AppDelegate
    0.13
    AppDelegate
    0.09
     Potato
    0.07
     poh
    0.07
    !..
    0.07
     Emoji
    0.06
    六
    0.06
     TypeScript
    0.06
    )application
    0.06
    explain
    0.06
    Activations Density 0.001%

    No Known Activations