© 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. 7-RESID-POST-AA
    6. 78855
    Prev
    Next
    INDEX
    Explanations

    done

    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
     kuruluş
    -0.07
     talep
    -0.07
     특히
    -0.07
     achieves
    -0.06
     مشاهده
    -0.06
     ux
    -0.06
    design
    -0.06
    isations
    -0.06
    IH
    -0.06
     sdf
    -0.06
    POSITIVE LOGITS
     mess
    0.07
     韓
    0.07
    sciously
    0.07
     Corona
    0.07
     clothes
    0.07
     Fors
    0.07
     worried
    0.06
     chops
    0.06
     Leaving
    0.06
     bunch
    0.06
    Activations Density 1.560%

    No Known Activations