© 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. 3-RESID-POST-AA
    11. 121769
    Prev
    Next
    INDEX
    Explanations

    Grand

    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
    ителем
    -0.07
     surgeries
    -0.06
     Bars
    -0.06
    /sc
    -0.06
     KN
    -0.06
     kvinna
    -0.06
     αυτό
    -0.06
     Mel
    -0.06
    ł
    -0.05
     sof
    -0.05
    POSITIVE LOGITS
     Grand
    0.32
    Grand
    0.25
     Grande
    0.13
    grand
    0.13
    -grand
    0.10
    rand
    0.10
     grandchildren
    0.09
     grandson
    0.08
     entrepreneurial
    0.08
     GTA
    0.08
    Activations Density 0.006%

    No Known Activations