Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 110708
    Prev
    Next
    INDEX
    Explanations

    Hair salons

    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
    �
    -0.07
    letes
    -0.06
    黑
    -0.06
     niž
    -0.06
    .evaluate
    -0.06
     Á
    -0.06
    Comparison
    -0.06
    _objs
    -0.06
    [text
    -0.06
     الكه
    -0.06
    POSITIVE LOGITS
    osi
    0.07
    ปลอดภ
    0.07
     defStyle
    0.07
    ielding
    0.06
    ButtonModule
    0.06
     �
    0.06
     trouver
    0.05
     tu
    0.05
    	operator
    0.05
     dhe
    0.05
    Activations Density 0.029%

    No Known Activations