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

    Neuronpedia

    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. 60457
    Prev
    Next
    INDEX
    Explanations

    phrases that express contrast or nuance in discussions

    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
    éĢ£
    -0.07
     ultimately
    -0.07
    lei
    -0.06
    Ñĩи
    -0.06
    .prepend
    -0.06
    ì²ľ
    -0.06
    sek
    -0.06
    .setViewport
    -0.06
    виÑĩ
    -0.06
    cola
    -0.06
    POSITIVE LOGITS
     still
    0.22
    still
    0.20
     continues
    0.19
     continue
    0.19
     Still
    0.19
    Still
    0.18
    ä»į
    0.16
     STILL
    0.16
     continued
    0.16
    continue
    0.16
    Activations Density 0.052%

    No Known Activations