© 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. 71126
    Prev
    Next
    INDEX
    Explanations

    instructions regarding medical consultation and medication use

    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
    furt
    -0.07
    wers
    -0.07
     ung
    -0.06
    lite
    -0.06
    浩
    -0.06
    reative
    -0.06
    excerpt
    -0.06
    intersection
    -0.06
    zik
    -0.06
     Folk
    -0.06
    POSITIVE LOGITS
    lec
    0.07
    ä»Ķ
    0.06
     defaultManager
    0.06
    ewis
    0.06
    veal
    0.06
    ök
    0.06
    avo
    0.06
    obao
    0.06
    ħĮ
    0.06
    oved
    0.06
    Activations Density 0.004%

    No Known Activations