© 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. 54653
    Prev
    Next
    INDEX
    Explanations

    punctuation and transitional phrases that indicate change or emphasis

    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
     Spinner
    -0.07
     Jak
    -0.06
     Microwave
    -0.06
    aul
    -0.06
     Guess
    -0.06
     dom
    -0.06
    erras
    -0.06
    arez
    -0.06
     Beach
    -0.06
    bish
    -0.06
    POSITIVE LOGITS
     dil
    0.07
    oure
    0.06
    аÑĤÑĭ
    0.06
     Accord
    0.06
     uniform
    0.06
     accord
    0.06
    asics
    0.06
     boot
    0.06
    ULSE
    0.06
    isclosed
    0.06
    Activations Density 0.001%

    No Known Activations