© 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. 9-LLAMASCOPE-RES-131K
    11. 97711
    Prev
    Next
    INDEX
    Explanations

    references to free resources or guides

    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
    endor
    -0.07
     clip
    -0.06
     mine
    -0.05
    deb
    -0.05
    溪
    -0.05
     persons
    -0.05
     ours
    -0.05
     dev
    -0.05
     paradox
    -0.05
     folk
    -0.05
    POSITIVE LOGITS
    ennon
    0.08
    ipel
    0.08
    iel
    0.08
    inkel
    0.07
    å·»
    0.07
    tero
    0.07
    angan
    0.07
    liner
    0.07
    zia
    0.07
    ãĥ©ãĤ¤ãĥĪ
    0.07
    Activations Density 0.012%

    No Known Activations