© 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. 57301
    Prev
    Next
    INDEX
    Explanations

    references to creators or individuals taking significant actions

    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
     Stap
    -0.07
    üml
    -0.07
     bilder
    -0.06
     perch
    -0.06
    erg
    -0.06
    N
    -0.06
    æĺ¯ä¸ª
    -0.06
    ú
    -0.06
     isError
    -0.06
     ìĿ´ëĬĶ
    -0.06
    POSITIVE LOGITS
    awei
    0.08
     closest
    0.07
    aylor
    0.07
    ighest
    0.07
    licative
    0.06
    most
    0.06
    ĻĤ
    0.06
    ije
    0.06
     least
    0.06
    OOM
    0.06
    Activations Density 0.032%

    No Known Activations