© 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. 60822
    Prev
    Next
    INDEX
    Explanations

    discussions around health and wellness, particularly focusing on nutritional aspects and dietary practices

    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
    lian
    -0.06
    servername
    -0.06
    º«
    -0.06
     Burr
    -0.06
    _clause
    -0.06
     ge
    -0.06
    diff
    -0.05
    gratis
    -0.05
    íķŃ
    -0.05
    oog
    -0.05
    POSITIVE LOGITS
     altogether
    0.09
     sight
    0.07
     Lose
    0.07
     perder
    0.07
    lose
    0.07
     loses
    0.07
    dre
    0.07
     lose
    0.07
    onas
    0.06
     contact
    0.06
    Activations Density 0.061%

    No Known Activations