© 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. 73715
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or qualifications to common rules or norms

    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
     otherwise
    -0.07
    pit
    -0.06
    cab
    -0.06
    òi
    -0.06
    æľŃ
    -0.06
     Otherwise
    -0.05
     Daw
    -0.05
     Ramsey
    -0.05
     Bail
    -0.05
    berapa
    -0.05
    POSITIVE LOGITS
    ikat
    0.08
    ubi
    0.07
    amina
    0.07
    ihat
    0.07
    boro
    0.07
    ilers
    0.07
    empor
    0.07
    ®
    0.07
    QUOTE
    0.07
    enthal
    0.07
    Activations Density 0.001%

    No Known Activations