© 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. 128501
    Prev
    Next
    INDEX
    Explanations

    references to natural disasters and their consequences

    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
    avou
    -0.07
    nech
    -0.07
    _terminal
    -0.07
    ulumi
    -0.07
    terminal
    -0.07
    ÃĹ↵↵
    -0.07
    ump
    -0.06
    ↵↵
    -0.06
     ogs
    -0.06
    flate
    -0.06
    POSITIVE LOGITS
    /dev
    0.07
     recent
    0.06
     bow
    0.06
    ooter
    0.06
    _MT
    0.06
     magnitude
    0.06
    aley
    0.06
    aster
    0.06
     freak
    0.06
    -dev
    0.06
    Activations Density 0.027%

    No Known Activations