© 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. 76458
    Prev
    Next
    INDEX
    Explanations

    concepts related to legislative or legal developments

    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
     currently
    -0.07
     always
    -0.07
    ninger
    -0.07
    chi
    -0.07
    always
    -0.06
    rets
    -0.06
    zdy
    -0.06
    Remaining
    -0.06
    hs
    -0.06
    immel
    -0.06
    POSITIVE LOGITS
     overnight
    0.09
     became
    0.08
    Become
    0.07
    Reusable
    0.07
     becomes
    0.07
    SelectionMode
    0.07
     Became
    0.07
    overn
    0.07
    bec
    0.07
    bens
    0.07
    Activations Density 0.129%

    No Known Activations