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. 14024
    Prev
    Next
    INDEX
    Explanations

    and, comma

    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
    _expression
    -0.07
     Bubble
    -0.06
    istance
    -0.06
    ۱۹۴
    -0.06
    _multiple
    -0.06
     European
    -0.06
    漂
    -0.06
    628
    -0.06
     Globe
    -0.06
    ros
    -0.06
    POSITIVE LOGITS
     Surv
    0.06
     فصل
    0.06
    gay
    0.06
     月
    0.06
    ぅ
    0.06
     уход
    0.06
    (robot
    0.06
    ّا
    0.06
     oui
    0.06
    --;
    0.06
    Activations Density 0.062%

    No Known Activations