Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 104285
    Prev
    Next
    INDEX
    Explanations

    :

    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
    centre
    -0.07
    ANCH
    -0.07
    /Add
    -0.07
    	attack
    -0.07
     thor
    -0.06
     incorrectly
    -0.06
     '$
    -0.06
    Timing
    -0.06
    	Write
    -0.06
     điểm
    -0.06
    POSITIVE LOGITS
     undertaken
    0.07
     днів
    0.07
    DG
    0.06
     Pets
    0.06
     suốt
    0.06
    *
    ↵
    0.06
    ежду
    0.06
     AudioClip
    0.06
    !↵↵↵↵↵↵
    0.06
    Includes
    0.06
    Activations Density 0.052%

    No Known Activations