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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93558
    Prev
    Next
    INDEX
    Explanations

    specific mathematical parameters and complex numerical data related to graphs and network theories

    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
    ected
    -0.06
     Kenn
    -0.06
     íıŃ
    -0.06
     lesbi
    -0.06
    [strlen
    -0.06
    039
    -0.06
     coc
    -0.06
    IST
    -0.06
    éĢł
    -0.06
     Dog
    -0.06
    POSITIVE LOGITS
     gig
    0.09
     thousands
    0.08
    unken
    0.08
    taire
    0.08
     thousand
    0.07
    oden
    0.07
     hundreds
    0.06
     hundred
    0.06
     Gig
    0.06
    elp
    0.06
    Activations Density 0.046%

    No Known Activations