© 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. 97959
    Prev
    Next
    INDEX
    Explanations

    references to the operating system and related commands

    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
    bidden
    -0.07
    mente
    -0.07
    shaw
    -0.07
    elle
    -0.07
    oning
    -0.07
    ment
    -0.06
    zeitig
    -0.06
    onation
    -0.06
    iston
    -0.06
    hare
    -0.06
    POSITIVE LOGITS
     Bened
    0.07
     way
    0.07
    oyer
    0.07
     apl
    0.06
    alice
    0.06
    yal
    0.06
    alis
    0.06
    viz
    0.06
    yas
    0.06
    ustos
    0.06
    Activations Density 0.001%

    No Known Activations