© 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. 75120
    Prev
    Next
    INDEX
    Explanations

    references to health benefits and nutritional value of foods

    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
    ifar
    -0.07
    wn
    -0.07
    ict
    -0.07
    urch
    -0.07
    -toast
    -0.07
    åħ¼
    -0.06
    ngör
    -0.06
     poisoned
    -0.06
    Injector
    -0.06
    _blend
    -0.06
    POSITIVE LOGITS
     fiber
    0.07
     Mick
    0.07
    夫
    0.07
     contents
    0.06
     ÙħÙĤ
    0.06
     antic
    0.06
     fibers
    0.06
     contains
    0.06
     Pist
    0.06
     contain
    0.06
    Activations Density 0.008%

    No Known Activations