© 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. 22-LLAMASCOPE-RES-131K
    11. 3941
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to dates or codes in technical or patent-related contexts

    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
     tur
    -0.07
    abr
    -0.07
    ustin
    -0.07
    azine
    -0.06
     tw
    -0.06
    swer
    -0.06
    gil
    -0.06
    wers
    -0.06
    fty
    -0.06
    еÑī
    -0.06
    POSITIVE LOGITS
    T
    0.08
    alse
    0.06
    DDS
    0.06
    /topics
    0.06
    mrt
    0.06
     Mills
    0.06
    adt
    0.06
    lut
    0.06
    ridged
    0.06
    Ý
    0.06
    Activations Density 0.021%

    No Known Activations