© 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. 62305
    Prev
    Next
    INDEX
    Explanations

    references to online content and interactions

    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
     paraph
    -0.07
    ac
    -0.06
     quote
    -0.06
     Lob
    -0.06
     pii
    -0.06
    ir
    -0.05
    hab
    -0.05
    âĢ¦↵
    -0.05
     Junk
    -0.05
    /entity
    -0.05
    POSITIVE LOGITS
    nero
    0.08
    past
    0.08
     posts
    0.08
     ARCH
    0.08
    earch
    0.08
    archives
    0.08
    quat
    0.08
    posts
    0.08
    elper
    0.08
     archives
    0.07
    Activations Density 0.019%

    No Known Activations