© 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. 15-LLAMASCOPE-RES-131K
    11. 89142
    Prev
    Next
    INDEX
    Explanations

    technical programming elements and structures

    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
    iasm
    -0.06
    ãģŁãģı
    -0.06
    \xff
    -0.06
    azzi
    -0.06
    ISA
    -0.06
    åł¡
    -0.06
    	LP
    -0.06
    .Args
    -0.06
    Formatted
    -0.06
    ação
    -0.06
    POSITIVE LOGITS
    jeta
    0.07
    Latch
    0.06
    urr
    0.06
    emin
    0.06
    raison
    0.06
    oom
    0.06
    iran
    0.06
    áže
    0.06
    bose
    0.06
    eton
    0.06
    Activations Density 0.018%

    No Known Activations