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. 58264
    Prev
    Next
    INDEX
    Explanations

    2

    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
    せて
    -0.07
     passer
    -0.07
    Cu
    -0.07
    ZX
    -0.07
     不
    -0.07
     개최
    -0.06
    VisualStyleBackColor
    -0.06
    igure
    -0.06
    fans
    -0.06
    .lift
    -0.06
    POSITIVE LOGITS
     shale
    0.07
     orange
    0.07
    ");}↵
    0.07
     abnormal
    0.06
     nerve
    0.06
    ())↵
    0.06
     QApplication
    0.06
    _extraction
    0.06
     architectures
    0.06
    amerate
    0.06
    Activations Density 0.007%

    No Known Activations