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. 80943
    Prev
    Next
    INDEX
    Explanations

    information

    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
     lest
    -0.07
    ab
    -0.06
    '*
    -0.06
    *p
    -0.06
     posterior
    -0.06
     cet
    -0.06
    �
    -0.06
    él
    -0.06
    .any
    -0.06
    407
    -0.06
    POSITIVE LOGITS
     information
    0.15
     Information
    0.13
    Information
    0.12
     INFORMATION
    0.11
    information
    0.11
     정보
    0.09
     informs
    0.09
     inform
    0.09
    .Information
    0.09
    Info
    0.08
    Activations Density 0.095%

    No Known Activations