© 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. 55982
    Prev
    Next
    INDEX
    Explanations

    phrases concerning medical advice and disclaimers

    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
    fty
    -0.08
    nox
    -0.07
    statuses
    -0.07
    å²³
    -0.07
    çİ
    -0.06
    óa
    -0.06
    antt
    -0.06
    ny
    -0.06
    DSA
    -0.06
     perf
    -0.06
    POSITIVE LOGITS
    stad
    0.07
    ults
    0.07
    atern
    0.07
    اÛĮÙĩ
    0.06
     treats
    0.06
     diag
    0.06
    finger
    0.06
    пеÑĩ
    0.06
     Dr
    0.06
     bordel
    0.06
    Activations Density 0.007%

    No Known Activations