© 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. 94611
    Prev
    Next
    INDEX
    Explanations

    concepts related to separation and division

    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
    estic
    -0.08
    ел
    -0.07
    erm
    -0.07
    пон
    -0.07
    èĬ
    -0.07
    presso
    -0.07
    hole
    -0.07
    erne
    -0.07
    ела
    -0.07
    eric
    -0.07
    POSITIVE LOGITS
    /div
    0.08
    stakes
    0.07
    /group
    0.07
    /se
    0.06
    ĶåĽŀ
    0.06
    -sex
    0.06
    ned
    0.06
    éĽ¢
    0.06
     biá»ĩt
    0.06
     Kas
    0.06
    Activations Density 0.016%

    No Known Activations