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. 11-RESID-POST-AA
    6. 84615
    Prev
    Next
    INDEX
    Explanations

    Derivatives

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “derivative.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orp
    -0.08
    श
    -0.07
    Gram
    -0.07
    ých
    -0.06
    ��
    -0.06
     liberalism
    -0.06
    添加
    -0.06
    .ids
    -0.06
     brace
    -0.06
    روب
    -0.06
    POSITIVE LOGITS
    /terms
    0.07
    @register
    0.06
     Rules
    0.06
     Hanging
    0.06
    reature
    0.06
    _BRANCH
    0.06
     stanice
    0.06
     aa
    0.06
    にある
    0.06
     roaring
    0.06
    Activations Density 0.007%

    No Known Activations