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. 104067
    Prev
    Next
    INDEX
    Explanations

    Legal issues

    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
     ajout
    -0.07
    ANGO
    -0.07
    IVEN
    -0.06
    ango
    -0.06
     lục
    -0.06
    iert
    -0.06
    fault
    -0.06
    YS
    -0.06
    celand
    -0.06
    _cnt
    -0.06
    POSITIVE LOGITS
     Caldwell
    0.07
    .Locale
    0.07
    PCM
    0.07
    Comparator
    0.07
    taxonomy
    0.06
     UE
    0.06
     희
    0.06
    high
    0.06
    riott
    0.06
     auss
    0.06
    Activations Density 0.040%

    No Known Activations