© 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. 129284
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in the."

    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
    umber
    -0.07
    achte
    -0.07
    ç¥
    -0.06
    appa
    -0.06
    erty
    -0.06
     å£
    -0.06
    osti
    -0.06
    edBy
    -0.06
    lets
    -0.06
    ucher
    -0.06
    POSITIVE LOGITS
    pose
    0.07
    (([
    0.06
    ÃŃch
    0.06
    mina
    0.06
    uye
    0.06
     instance
    0.06
    è¶Ĭ
    0.06
    DTD
    0.06
    رÙĬÙģ
    0.06
    duk
    0.06
    Activations Density 0.022%

    No Known Activations