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. 11-RESID-POST-AA
    6. 118350
    Prev
    Next
    INDEX
    Explanations

    Cytochrome P450 enzymes

    np_max-act · gemini-2.0-flash

    genes related to cytochrome P450 enzymes involved in drug metabolism.

    oai_token-act-pair · gpt-4o-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
    -handler
    -0.07
    DMA
    -0.07
    žil
    -0.06
     userManager
    -0.06
    mist
    -0.06
    weise
    -0.06
    Histogram
    -0.06
     loader
    -0.06
    Hide
    -0.06
    mini
    -0.06
    POSITIVE LOGITS
     �
    0.07
    อำ
    0.07
    	GLuint
    0.07
    /api
    0.06
    ='.
    0.06
     Franken
    0.06
    =tf
    0.06
     lawsuits
    0.06
    /im
    0.06
     สพ
    0.06
    Activations Density 0.003%

    No Known Activations