© 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. 57939
    Prev
    Next
    INDEX
    Explanations

    patterns and transitions in post sequences

    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
    .im
    -0.07
    GI
    -0.06
    imming
    -0.06
    ullan
    -0.06
    ÅĻi
    -0.06
    Handle
    -0.06
     im
    -0.06
    voj
    -0.06
    itches
    -0.06
    oure
    -0.06
    POSITIVE LOGITS
     Does
    0.09
     Ø¢ÛĮا
    0.09
     does
    0.08
     why
    0.08
    —is
    0.08
     Why
    0.08
     What
    0.08
     How
    0.08
     Who
    0.07
     how
    0.07
    Activations Density 0.025%

    No Known Activations