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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 54318
    Prev
    Next
    INDEX
    Explanations

    collectible card games

    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
     CCD
    -0.07
     genotype
    -0.07
    ccc
    -0.06
    opening
    -0.06
     goof
    -0.06
     Bach
    -0.06
    ophon
    -0.06
     Allocate
    -0.06
     Cbd
    -0.06
     Composition
    -0.06
    POSITIVE LOGITS
    ем
    0.06
    .format
    0.06
    jango
    0.06
    _application
    0.06
    _subplot
    0.06
     trusts
    0.06
    	bg
    0.06
    leta
    0.06
    adolu
    0.06
    }',
    0.06
    Activations Density 0.013%

    No Known Activations