© 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 EvalsExportsinterp-engineNEWAPI 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. 86652
    Prev
    Next
    INDEX
    Explanations

    verbs associated with physical actions and events

    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
    غات
    -0.08
     EITHER
    -0.07
    اذا
    -0.07
     FindObjectOfType
    -0.07
     typealias
    -0.07
     treff
    -0.07
    plex
    -0.07
    chyb
    -0.07
    536
    -0.07
    olas
    -0.07
    POSITIVE LOGITS
     another
    0.13
     other
    0.11
    another
    0.09
     two
    0.09
     several
    0.08
     nearby
    0.08
    other
    0.07
     others
    0.07
     Another
    0.07
    åı¦ä¸Ģ
    0.07
    Activations Density 0.041%

    No Known Activations