© 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. 72618
    Prev
    Next
    INDEX
    Explanations

    actions and their execution

    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
    etched
    -0.07
    egov
    -0.07
    ampo
    -0.07
    _ATTRIB
    -0.07
    aybe
    -0.07
    antly
    -0.07
    NCY
    -0.07
    iple
    -0.07
    fy
    -0.06
    нед
    -0.06
    POSITIVE LOGITS
     things
    0.07
     Stuff
    0.06
     tasks
    0.06
    ibus
    0.06
    WithType
    0.06
    _stuff
    0.06
    things
    0.06
    urious
    0.06
     Things
    0.06
    Things
    0.06
    Activations Density 0.031%

    No Known Activations