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. 14870
    Prev
    Next
    INDEX
    Explanations

    period

    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
     کوتاه
    -0.07
     unwitting
    -0.07
    ौट
    -0.07
     состоит
    -0.07
    uetooth
    -0.07
    _chunk
    -0.06
    ("/
    -0.06
    ulur
    -0.06
    ่อไป
    -0.06
     Так
    -0.06
    POSITIVE LOGITS
     edin
    0.07
     Kata
    0.06
     haft
    0.06
     brace
    0.06
    iet
    0.06
    laughs
    0.06
     ratt
    0.06
    [sub
    0.06
    inez
    0.06
    lerini
    0.06
    Activations Density 0.053%

    No Known Activations