© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61430
    Prev
    Next
    INDEX
    Explanations

    programming functions and methods related to data manipulation or processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aar
    -0.07
     alt
    -0.06
    ooter
    -0.06
    .scalablytyped
    -0.06
    arro
    -0.06
     Car
    -0.06
     Lake
    -0.06
    TypeInfo
    -0.06
    ift
    -0.06
     i
    -0.06
    POSITIVE LOGITS
     подоб
    0.07
    иÑİ
    0.07
    uges
    0.06
    Returning
    0.06
    å±
    0.06
    WARDS
    0.06
    ERO
    0.06
    oku
    0.06
    743
    0.06
    адки
    0.06
    Activations Density 0.019%

    No Known Activations