© 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. 15-LLAMASCOPE-RES-131K
    11. 87839
    Prev
    Next
    INDEX
    Explanations

    terms related to multi-functional or multi-faceted systems and structures

    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
    enské
    -0.07
    wij
    -0.07
    UNET
    -0.07
    rawn
    -0.07
    _RECEIVED
    -0.07
    tak
    -0.07
    ظÙĩ
    -0.07
    má
    -0.07
    MOTE
    -0.07
    tesy
    -0.07
    POSITIVE LOGITS
    /single
    0.07
    -multi
    0.07
     complex
    0.06
    -mult
    0.06
    -
    0.06
     Complex
    0.06
     Pom
    0.06
    /m
    0.06
     aspect
    0.06
     nature
    0.05
    Activations Density 0.028%

    No Known Activations