© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82214
    Prev
    Next
    INDEX
    Explanations

    causative factors and conditions related to health issues, particularly arthritis and associated diseases

    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
    çĬ
    -0.07
    fect
    -0.07
    ÙĤÛĮ
    -0.07
    Ïģαν
    -0.07
    _utilities
    -0.07
    ABCDEFGHI
    -0.06
    ardon
    -0.06
    aders
    -0.06
     вб
    -0.06
     moc
    -0.06
    POSITIVE LOGITS
     developing
    0.08
     develop
    0.08
     risk
    0.08
     develops
    0.07
    develop
    0.07
     later
    0.06
    czy
    0.06
     susceptibility
    0.06
    -develop
    0.06
    åĥį
    0.06
    Activations Density 0.022%

    No Known Activations