© 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. 125974
    Prev
    Next
    INDEX
    Explanations

    references to accuracy and precision in information or context

    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
    uggy
    -0.07
    ropa
    -0.07
    chy
    -0.06
     vestib
    -0.06
    lep
    -0.06
     tail
    -0.06
    _blocking
    -0.06
    358
    -0.06
     sacr
    -0.06
    害
    -0.06
    POSITIVE LOGITS
    erin
    0.08
    ifice
    0.07
    رÙĬÙħ
    0.07
    sed
    0.07
    dest
    0.07
    ilib
    0.07
    ëŀ
    0.07
    ivent
    0.07
    fik
    0.06
     Hosp
    0.06
    Activations Density 0.003%

    No Known Activations