© 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 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. 85748
    Prev
    Next
    INDEX
    Explanations

    keywords related to the beginning and ending of sections in documents or scripts

    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
    jvu
    -0.08
    itesse
    -0.07
    elli
    -0.07
     DONE
    -0.07
    eteria
    -0.07
    ules
    -0.07
    æ£Ĵ
    -0.07
    immel
    -0.06
    abin
    -0.06
    lenir
    -0.06
    POSITIVE LOGITS
    chwitz
    0.07
    876
    0.06
    /up
    0.06
     shame
    0.06
    547
    0.06
     ob
    0.06
    sWith
    0.06
     gross
    0.06
     rem
    0.06
     Gross
    0.05
    Activations Density 0.004%

    No Known Activations