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. 42070
    Prev
    Next
    INDEX
    Explanations

    detector

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of detection equipment and measurement instruments—especially words like “detector,” “scintillator,” and related sensing devices.

    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
    '↵↵
    -0.08
     transformations
    -0.07
    -hit
    -0.07
     ста
    -0.07
    ))↵↵
    -0.06
    Translator
    -0.06
     shadows
    -0.06
    	menu
    -0.06
    cling
    -0.06
    ));↵↵↵
    -0.06
    POSITIVE LOGITS
    >Type
    0.06
     artış
    0.06
    ồng
    0.06
    _Abstract
    0.06
     estaba
    0.06
    �
    0.06
     doivent
    0.06
     अवध
    0.06
     ділян
    0.06
    ughters
    0.06
    Activations Density 0.027%

    No Known Activations