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

    Neuronpedia

    Jacobian LensNEW
    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. 130390
    Prev
    Next
    INDEX
    Explanations

    references to academic or scientific research findings

    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
    urette
    -0.07
    âce
    -0.06
    Intialized
    -0.06
    ugu
    -0.06
    505
    -0.06
    ouser
    -0.06
    aml
    -0.06
    	TokenName
    -0.06
    ortex
    -0.06
    peq
    -0.06
    POSITIVE LOGITS
    geom
    0.07
    kaar
    0.07
    ÑĶм
    0.06
    ĸī
    0.06
    _RECEIVED
    0.06
    -Out
    0.06
    oha
    0.06
    COND
    0.06
    ActivityIndicator
    0.06
    AILY
    0.06
    Activations Density 0.000%

    No Known Activations