© 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. 108295
    Prev
    Next
    INDEX
    Explanations

    mentions of committees or committee-related contexts

    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
    /sm
    -0.08
    çĦ¶
    -0.08
    HOOK
    -0.08
    ëį°
    -0.07
    aney
    -0.07
    leta
    -0.07
    meth
    -0.07
    ruba
    -0.07
    ifter
    -0.07
     -*-č↵
    -0.07
    POSITIVE LOGITS
     members
    0.08
    tees
    0.08
    tee
    0.07
    mts
    0.07
    artment
    0.07
    asts
    0.07
    atical
    0.06
    ares
    0.06
    \HttpFoundation
    0.06
    ulum
    0.06
    Activations Density 0.013%

    No Known Activations