© 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. 104448
    Prev
    Next
    INDEX
    Explanations

    references to documents and associated services or legitimacy

    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
    å£ģ
    -0.06
    ence
    -0.06
    inkel
    -0.06
    Squared
    -0.06
     Contributor
    -0.06
    pure
    -0.06
    طة
    -0.06
    iqu
    -0.06
     Cord
    -0.06
    ataloader
    -0.06
    POSITIVE LOGITS
     legit
    0.08
     fake
    0.08
     Mim
    0.07
    plib
    0.07
     Tro
    0.07
     Nursing
    0.07
     nursing
    0.06
     Fake
    0.06
     mar
    0.06
    fak
    0.06
    Activations Density 0.001%

    No Known Activations