© 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. 55222
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate exceptions or limitations in statements

    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
     både
    -0.08
    ilos
    -0.08
    igan
    -0.07
    alles
    -0.07
     tháºŃm
    -0.07
    iele
    -0.07
    owie
    -0.07
     BOTH
    -0.06
    ãģ¾ãģŁ
    -0.06
    dorf
    -0.06
    POSITIVE LOGITS
     occasional
    0.12
     few
    0.11
     occasionally
    0.09
     exception
    0.09
     exceptions
    0.09
    few
    0.09
     maybe
    0.09
     Exceptions
    0.09
     Few
    0.09
     minor
    0.09
    Activations Density 0.023%

    No Known Activations