© 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. 31554
    Prev
    Next
    INDEX
    Explanations

    Reasoning/explanation

    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
    ===
    -0.07
    RootElement
    -0.07
     along
    -0.06
    otle
    -0.06
    LEAN
    -0.06
    ographs
    -0.06
     Rowling
    -0.06
    ien
    -0.06
    δή
    -0.06
     fabrics
    -0.06
    POSITIVE LOGITS
     vandal
    0.07
    .Ver
    0.06
     lessen
    0.06
     conclusive
    0.06
     Gerr
    0.06
     Param
    0.06
     nov
    0.06
     effic
    0.06
     JMenuItem
    0.06
     pak
    0.06
    Activations Density 0.034%

    No Known Activations