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. 110343
    Prev
    Next
    INDEX
    Explanations

    libel and defamation

    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
    ミュ
    -0.07
    ूक
    -0.07
     EI
    -0.06
     annoy
    -0.06
    ließ
    -0.06
     طبق
    -0.06
     mają
    -0.06
    iciency
    -0.06
     competition
    -0.06
     enn
    -0.06
    POSITIVE LOGITS
    :Any
    0.07
     تط
    0.06
    RIX
    0.06
    -res
    0.06
     باشگاه
    0.06
    077
    0.06
     glam
    0.06
     gx
    0.06
    letic
    0.06
    .intersection
    0.06
    Activations Density 0.016%

    No Known Activations