© 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. 82321
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating relationships or origins

    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
     itself
    -0.09
    .LayoutStyle
    -0.09
    aign
    -0.08
    raya
    -0.08
    frei
    -0.08
    mite
    -0.08
     ydk
    -0.08
    /../
    -0.08
    ITIZE
    -0.08
    ฬ
    -0.08
    POSITIVE LOGITS
     various
    0.10
     themselves
    0.08
     who
    0.08
     whom
    0.08
     both
    0.07
    innen
    0.07
     everywhere
    0.07
     other
    0.06
     backgrounds
    0.06
     Stephen
    0.06
    Activations Density 0.053%

    No Known Activations