© 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. 119324
    Prev
    Next
    INDEX
    Explanations

    the word "and" 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
    une
    -0.06
    aque
    -0.06
     Fuller
    -0.06
    hurst
    -0.06
    early
    -0.06
    allest
    -0.06
    Ñĥж
    -0.05
    зÑĭ
    -0.05
    Ñģ
    -0.05
    quent
    -0.05
    POSITIVE LOGITS
     Uncategorized
    0.12
     tagged
    0.09
    WithTag
    0.08
     permalink
    0.07
    žel
    0.07
    /fw
    0.07
    iffer
    0.07
    hta
    0.07
     Tag
    0.07
     Tags
    0.07
    Activations Density 0.002%

    No Known Activations