© 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. 84096
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency in the text

    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
    fore
    -0.07
    orer
    -0.06
    à¸Ĺย
    -0.06
     nowhere
    -0.06
    onec
    -0.06
    HandlerContext
    -0.06
    _PM
    -0.06
    OMP
    -0.06
    акÑģим
    -0.06
    {@
    -0.06
    POSITIVE LOGITS
     whereas
    0.14
     meanwhile
    0.11
     Whereas
    0.11
     Meanwhile
    0.11
    Meanwhile
    0.09
    ï¼ĮèĢĮ
    0.09
     whilst
    0.08
     while
    0.08
     èĢĮ
    0.07
     Conversely
    0.07
    Activations Density 0.045%

    No Known Activations