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. 16204
    Prev
    Next
    INDEX
    Explanations

    legal judgments

    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
    .ff
    -0.07
     헤
    -0.06
     CSV
    -0.06
     Illustrator
    -0.06
    Reality
    -0.06
    _PTR
    -0.06
    msgs
    -0.06
     RDD
    -0.06
     Empty
    -0.06
    ("@
    -0.06
    POSITIVE LOGITS
     knees
    0.07
    .platform
    0.07
    こう
    0.07
     onset
    0.07
     guarantees
    0.07
     απο
    0.06
     backers
    0.06
     post
    0.06
     좋
    0.06
     pre
    0.06
    Activations Density 0.001%

    No Known Activations