© 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. 11-RESID-POST-AA
    11. 19962
    Prev
    Next
    INDEX
    Explanations

    show

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prophets
    -0.07
    	fclose
    -0.06
    AppState
    -0.06
    лоб
    -0.06
     있다는
    -0.06
    Para
    -0.06
     гром
    -0.06
    parency
    -0.06
    paralle
    -0.06
    धर
    -0.05
    POSITIVE LOGITS
     formato
    0.08
    τς
    0.07
     thoải
    0.07
     ı
    0.07
     SSD
    0.07
     unrestricted
    0.06
     Marketing
    0.06
    ÔNG
    0.06
    =.
    0.06
    _listing
    0.06
    Activations Density 0.012%

    No Known Activations