© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75306
    Prev
    Next
    INDEX
    Explanations

    references to healthcare-related protections and issues

    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
     healthcare
    -0.09
     Healthcare
    -0.08
     Provid
    -0.07
    #af
    -0.07
    á»ijn
    -0.07
    oppel
    -0.06
    éĽª
    -0.06
    _sequences
    -0.06
    Doctors
    -0.06
    غÙħ
    -0.06
    POSITIVE LOGITS
    uya
    0.07
     Peach
    0.06
     solid
    0.06
    ikon
    0.06
    alytics
    0.06
     expanded
    0.06
    yon
    0.06
     Grimm
    0.06
     baud
    0.06
     Bug
    0.06
    Activations Density 0.015%

    No Known Activations