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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 53850
    Prev
    Next
    INDEX
    Explanations

    return

    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
    Medium
    -0.06
    xe
    -0.06
     dioxide
    -0.06
     Edwin
    -0.06
     drawbacks
    -0.06
     terrace
    -0.06
     OFFSET
    -0.06
    Latch
    -0.06
    _df
    -0.06
    Xem
    -0.06
    POSITIVE LOGITS
    eleri
    0.07
     pic
    0.07
     Articles
    0.06
    forma
    0.06
    804
    0.06
    ,'%
    0.06
    _rng
    0.06
    ması
    0.06
     editorial
    0.06
    asco
    0.06
    Activations Density 0.014%

    No Known Activations