© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129025
    Prev
    Next
    INDEX
    Explanations

    references to searching for and resolving software bugs and technical issues

    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
     takson
    -0.07
    erie
    -0.07
    ripp
    -0.06
    ìĪĺë¡ľ
    -0.06
    bei
    -0.06
    -transitional
    -0.06
    opolitan
    -0.06
    taj
    -0.06
    space
    -0.06
    rape
    -0.06
    POSITIVE LOGITS
     source
    0.10
     identification
    0.09
     trace
    0.09
     identifies
    0.09
     identify
    0.09
     traced
    0.09
     Identify
    0.09
    identify
    0.08
     Identification
    0.08
     sources
    0.08
    Activations Density 0.055%

    No Known Activations