© 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. 62566
    Prev
    Next
    INDEX
    Explanations

    references to legal case numbers or citations

    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
    etler
    -0.09
    maal
    -0.07
    lrt
    -0.07
    et
    -0.07
    ew
    -0.07
    ijn
    -0.07
    eya
    -0.07
    mdi
    -0.07
    istrovstvÃŃ
    -0.07
    iap
    -0.07
    POSITIVE LOGITS
    smith
    0.09
    les
    0.09
    vals
    0.09
    son
    0.08
    Ù
    0.07
    sons
    0.07
    ating
    0.07
    /name
    0.07
    fully
    0.07
    ếp
    0.07
    Activations Density 0.067%

    No Known Activations