© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106517
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" and its variations in various 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
    i
    -0.09
    ÛĮ
    -0.09
    tv
    -0.09
    hots
    -0.09
    tf
    -0.09
    tm
    -0.09
    hem
    -0.08
    tc
    -0.08
    haus
    -0.08
    hal
    -0.08
    POSITIVE LOGITS
    ãĤ±ãĥĥãĥĪ
    0.08
    nel
    0.08
    ras
    0.07
    ÙĨاÙħÙĩ
    0.07
    aland
    0.07
    евиÑĩ
    0.07
    ht
    0.07
    aurus
    0.07
    ny
    0.07
    ̧
    0.07
    Activations Density 0.062%

    No Known Activations