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

    Neuronpedia

    Jacobian LensNEW
    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. 88503
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and collections

    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
     Destructor
    -0.07
    uetype
    -0.07
    alı
    -0.07
    atility
    -0.07
    EncodingException
    -0.06
    à¸ļาล
    -0.06
    thumb
    -0.06
    gend
    -0.06
    iegel
    -0.06
    yd
    -0.06
    POSITIVE LOGITS
    arrants
    0.06
    ]|[
    0.06
     bast
    0.06
    пон
    0.06
    mare
    0.06
    ivan
    0.06
     Gast
    0.06
    éĻ¢
    0.06
    arrant
    0.06
    chain
    0.06
    Activations Density 0.011%

    No Known Activations