© 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. 78102
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions or symptoms

    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
     worst
    -0.08
     inf
    -0.07
     worse
    -0.07
    λοÏħ
    -0.06
    vester
    -0.06
    amber
    -0.06
    pto
    -0.06
    ¤
    -0.06
     Inf
    -0.06
     Worst
    -0.06
    POSITIVE LOGITS
    zens
    0.08
    .scalablytyped
    0.07
    eyse
    0.07
    itarian
    0.06
    arena
    0.06
    swire
    0.06
    yte
    0.06
    namen
    0.06
     Cotton
    0.06
    daemon
    0.06
    Activations Density 0.030%

    No Known Activations