© 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. 98253
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions and specifications for certain technical functions or options

    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
    ãĤ¤ãĥĦ
    -0.07
    allas
    -0.07
    dre
    -0.06
    ominated
    -0.06
    _RC
    -0.06
    å¥ij
    -0.06
    OSC
    -0.06
    alem
    -0.06
    èm
    -0.06
    Mapping
    -0.06
    POSITIVE LOGITS
    utton
    0.07
    TreeWidgetItem
    0.06
     Rev
    0.06
    uns
    0.06
    uru
    0.06
     standout
    0.06
    ort
    0.06
    ades
    0.06
    shade
    0.06
    dash
    0.06
    Activations Density 0.300%

    No Known Activations