© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 78962
    Prev
    Next
    INDEX
    Explanations

    elements related to grouping and categorization in mathematical or statistical contexts

    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
    phinx
    -0.09
    \grid
    -0.09
    ertino
    -0.08
    (çģ«
    -0.08
    adge
    -0.07
     mastur
    -0.07
    (æ°´
    -0.07
    ɵ
    -0.07
     hra
    -0.07
    zag
    -0.07
    POSITIVE LOGITS
    dit
    0.10
     dit
    0.09
     likewise
    0.07
     Dit
    0.07
     Likewise
    0.07
     similarly
    0.06
     ìĹŃìĭľ
    0.06
    lik
    0.06
     lean
    0.06
     naopak
    0.06
    Activations Density 0.062%

    No Known Activations