© 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 EvalsExportsinterp-engineNEWAPI 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. 15040
    Prev
    Next
    INDEX
    Explanations

    words that indicate a minimal quantity or scarcity

    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
    éĤ¦
    -0.07
    anki
    -0.07
    znik
    -0.06
     án
    -0.06
    ifest
    -0.06
     Alphabet
    -0.06
    hci
    -0.06
    à¸ģระ
    -0.06
    óa
    -0.06
    abin
    -0.06
    POSITIVE LOGITS
    179
    0.08
    apis
    0.07
    Disposed
    0.07
    711
    0.07
     ruling
    0.07
    ombat
    0.07
    ãĤ¥
    0.06
    dispose
    0.06
     Compatible
    0.06
     disposal
    0.06
    Activations Density 0.000%

    No Known Activations