© 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. 125052
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a priority or first-come, first-served policy

    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
    tran
    -0.07
    oyo
    -0.07
    _HC
    -0.06
    ürn
    -0.06
    ilir
    -0.06
    _arrays
    -0.06
    ekler
    -0.06
    ī´
    -0.06
    earth
    -0.06
    esi
    -0.06
    POSITIVE LOGITS
    /rc
    0.07
    uft
    0.07
     order
    0.07
    izzle
    0.06
    /request
    0.06
    adle
    0.06
    ione
    0.06
    Entered
    0.06
    chaft
    0.06
    iegel
    0.06
    Activations Density 0.003%

    No Known Activations