© 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. 11-RESID-POST-AA
    6. 65834
    Prev
    Next
    INDEX
    Explanations

    return

    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
     Herald
    -0.07
     lựa
    -0.06
     harmless
    -0.06
     Naw
    -0.06
    erek
    -0.06
     tk
    -0.06
     Amend
    -0.06
     ("
    -0.06
    -direct
    -0.06
    -role
    -0.06
    POSITIVE LOGITS
    	continue
    0.07
     reconstruction
    0.06
    �
    0.06
    ptype
    0.06
    _popup
    0.06
     dejar
    0.06
    ैं।↵↵
    0.06
    	finally
    0.06
    ै?↵
    0.06
    函
    0.06
    Activations Density 0.006%

    No Known Activations