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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 91046
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]];↵
    -0.07
    	Texture
    -0.06
    ."));↵
    -0.06
    (Encoding
    -0.06
    _container
    -0.06
    urface
    -0.06
    城市
    -0.06
     Formula
    -0.06
     ');
    -0.06
     smash
    -0.06
    POSITIVE LOGITS
     düşman
    0.07
     unprotected
    0.06
    Journal
    0.06
     střed
    0.06
     FullName
    0.06
     deactivated
    0.06
     مج
    0.06
    apeake
    0.06
    ONGO
    0.06
     miss
    0.06
    Activations Density 0.027%

    No Known Activations