© 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. 9-LLAMASCOPE-RES-131K
    11. 96552
    Prev
    Next
    INDEX
    Explanations

    mentions of issues related to software dependencies and their status

    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
    ÃľM
    -0.09
    INSTANCE
    -0.08
    otta
    -0.08
     ëĦ¤ìĿ´íĬ¸
    -0.08
    Ä°Y
    -0.08
    asca
    -0.07
    .Registry
    -0.07
    iete
    -0.07
    /Grid
    -0.07
    acam
    -0.07
    POSITIVE LOGITS
     since
    0.07
    isd
    0.06
     Mapper
    0.06
     literally
    0.06
     def
    0.05
     history
    0.05
     now
    0.05
     Jensen
    0.05
     Morales
    0.05
     Tobias
    0.05
    Activations Density 0.001%

    No Known Activations