© 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. 80281
    Prev
    Next
    INDEX
    Explanations

    references to parallel processing and testing methods

    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
    iros
    -0.08
    etch
    -0.07
    quate
    -0.07
    lÃŃÄį
    -0.07
    ãĤ£
    -0.07
    PointerException
    -0.07
    sey
    -0.07
    ael
    -0.07
    tabpanel
    -0.07
    oard
    -0.07
    POSITIVE LOGITS
    ness
    0.08
    izable
    0.08
    ism
    0.08
    ity
    0.08
    OUS
    0.07
    ized
    0.07
    ize
    0.06
    791
    0.06
     rep
    0.06
    ør
    0.06
    Activations Density 0.012%

    No Known Activations