© 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. 87217
    Prev
    Next
    INDEX
    Explanations

    references to educational training programs

    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
     courtesy
    -0.06
    erken
    -0.06
    alan
    -0.06
    otland
    -0.06
    oom
    -0.06
     separ
    -0.06
    endale
    -0.06
     strtol
    -0.06
    ERC
    -0.06
     Baz
    -0.06
    POSITIVE LOGITS
    trainer
    0.07
    _hyper
    0.07
     trainers
    0.07
     advance
    0.06
    .Pass
    0.06
    мм
    0.06
    _mapper
    0.06
     scen
    0.06
     PACKAGE
    0.06
    blr
    0.06
    Activations Density 0.008%

    No Known Activations