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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 53278
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     th
    -0.07
     Geneva
    -0.07
     ई
    -0.07
    [MAXN
    -0.06
    (outfile
    -0.06
    ených
    -0.06
     gio
    -0.06
    [label
    -0.06
    려요
    -0.06
     taller
    -0.06
    POSITIVE LOGITS
    NECTION
    0.07
    touches
    0.07
     graphics
    0.07
    _ed
    0.06
    297
    0.06
    .part
    0.06
     marriages
    0.06
    .production
    0.06
    _tuples
    0.06
    ัดส
    0.06
    Activations Density 0.033%

    No Known Activations