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. 3-RESID-POST-AA
    6. 122774
    Prev
    Next
    INDEX
    Explanations

    non-english, "surprising" words

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     denně
    -0.07
     theta
    -0.06
    ीप
    -0.06
     knew
    -0.06
    )test
    -0.06
     colorful
    -0.06
    .lookup
    -0.05
     Richards
    -0.05
     věcí
    -0.05
     و
    -0.05
    POSITIVE LOGITS
    prend
    0.08
     удив
    0.08
     astounding
    0.08
     Ridley
    0.08
     tacos
    0.07
     Quite
    0.07
     surpr
    0.07
    ποι
    0.06
    _caption
    0.06
    टक
    0.06
    Activations Density 0.015%

    No Known Activations