© 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. 85219
    Prev
    Next
    INDEX
    Explanations

    warnings related to health and safety risks

    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
     amen
    -0.06
     curs
    -0.06
    quiry
    -0.06
     abort
    -0.06
     decide
    -0.06
     inquiry
    -0.05
    owan
    -0.05
    ,
    -0.05
    oco
    -0.05
     atmosphere
    -0.05
    POSITIVE LOGITS
     tips
    0.10
    tips
    0.08
    Tips
    0.08
     Tips
    0.08
     обÑĢаÑī
    0.07
     tip
    0.07
    ÑĢÑı
    0.07
    Tip
    0.07
     }?>↵
    0.07
     urges
    0.07
    Activations Density 0.037%

    No Known Activations