© 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. 128859
    Prev
    Next
    INDEX
    Explanations

    coding terms and classifications related to data structures and shader programming

    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
    ầy
    -0.07
    AndWait
    -0.07
    ÄĽtÅ¡
    -0.07
    engin
    -0.07
    HECK
    -0.07
     cigaret
    -0.07
    иÑģлов
    -0.07
    êt
    -0.06
    herit
    -0.06
    Ấ
    -0.06
    POSITIVE LOGITS
    ::
    0.14
    :
    0.08
    ://
    0.07
    ical
    0.07
    's
    0.07
     Abuse
    0.07
    Ùĭ
    0.06
    ’s
    0.06
    esian
    0.06
    ®
    0.06
    Activations Density 0.012%

    No Known Activations