© 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. 5-LLAMASCOPE-RES-131K
    11. 126047
    Prev
    Next
    INDEX
    Explanations

    phrases related to rates and ratios

    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
    ellung
    -0.07
    agara
    -0.07
     Crew
    -0.07
    áÄį
    -0.07
    oute
    -0.07
    ytt
    -0.06
    au
    -0.06
    arrant
    -0.06
    aviours
    -0.06
    ague
    -0.06
    POSITIVE LOGITS
    æľºåħ³
    0.07
     Mey
    0.06
    ysl
    0.06
     prec
    0.06
    conde
    0.06
    CEL
    0.06
     NTN
    0.06
    antium
    0.06
    inho
    0.06
     UIApplication
    0.05
    Activations Density 0.002%

    No Known Activations