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. 7-RESID-POST-AA
    6. 93485
    Prev
    Next
    INDEX
    Explanations

    seizure

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    čný
    -0.07
    acf
    -0.07
    loth
    -0.07
    ogne
    -0.06
    ΑΝΤ
    -0.06
     Arbeit
    -0.06
    li
    -0.06
     bức
    -0.06
     vznik
    -0.06
     machen
    -0.06
    POSITIVE LOGITS
     seizures
    0.14
     seizure
    0.13
     З
    0.07
     gi�
    0.07
    Saturday
    0.06
    _su
    0.06
     SU
    0.06
     SE
    0.06
     Пер
    0.06
    (check
    0.06
    Activations Density 0.001%

    No Known Activations