Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5742
    Prev
    Next
    INDEX
    Explanations

    details related to crises or critical events

    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
     "$
    -0.08
    onda
    -0.07
    ï¼ģï¼ģ↵↵
    -0.07
     butto
    -0.07
    uhe
    -0.07
    ahas
    -0.06
     "`
    -0.06
     $
    -0.06
     Aws
    -0.06
    okens
    -0.06
    POSITIVE LOGITS
     vids
    0.07
    mgr
    0.06
     tetas
    0.06
    ccd
    0.06
    978
    0.06
     nos
    0.06
    )","
    0.06
    CESS
    0.06
    lÃŃn
    0.06
    .mods
    0.06
    Activations Density 0.050%

    No Known Activations