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. 27-RESID-POST-AA
    6. 9256
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     errs
    -0.07
    Permissions
    -0.07
    (),↵↵
    -0.07
    ảng
    -0.07
    íř
    -0.07
     �
    -0.07
    /////
    -0.07
    ));
    ↵
    ↵
    -0.07
    'autres
    -0.07
    \modules
    -0.06
    POSITIVE LOGITS
     psychic
    0.06
     professional
    0.06
    Operations
    0.06
    BE
    0.06
     nuis
    0.06
    <TreeNode
    0.06
     Seahawks
    0.06
     […
    0.06
    ovit
    0.05
    	self
    0.05
    Activations Density 0.020%

    No Known Activations