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. 34470
    Prev
    Next
    INDEX
    Explanations

    Devices and assembly

    np_max-act · gemini-2.0-flash

    inventions related to cleaning devices or systems, particularly those used in smoking apparatuses.

    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
     dirty
    -0.08
    /<
    -0.07
    ức
    -0.07
    =<
    -0.07
    fal
    -0.07
     prev
    -0.07
    	dd
    -0.06
     ref
    -0.06
    yle
    -0.06
    _coeffs
    -0.06
    POSITIVE LOGITS
    ัวร
    0.06
     almak
    0.06
    เภท
    0.06
     büny
    0.06
    ्षण
    0.06
     muy
    0.06
     είχαν
    0.05
     manganese
    0.05
    _logs
    0.05
    иров
    0.05
    Activations Density 0.057%

    No Known Activations