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. 15-RESID-POST-AA
    6. 54199
    Prev
    Next
    INDEX
    Explanations

    Narratives

    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
     verte
    -0.08
    сен
    -0.07
    _planes
    -0.07
     recruiting
    -0.07
    .
    ↵
    ↵
    -0.07
    placements
    -0.07
     peaks
    -0.07
    Portrait
    -0.07
     chicks
    -0.07
    ara
    -0.07
    POSITIVE LOGITS
    ickém
    0.06
     misery
    0.06
    -wh
    0.06
    _regeneration
    0.06
    .Raise
    0.06
    .TestCheck
    0.06
    -move
    0.06
     midway
    0.06
     однов
    0.06
    .listener
    0.05
    Activations Density 0.088%

    No Known Activations