© 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. 15-LLAMASCOPE-RES-131K
    11. 86649
    Prev
    Next
    INDEX
    Explanations

    terms related to the GNU project and its software documentation

    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
    iese
    -0.06
     unlikely
    -0.06
    lem
    -0.06
    lat
    -0.06
    ulet
    -0.06
    rese
    -0.06
    [][
    -0.05
    ustr
    -0.05
    leh
    -0.05
    lying
    -0.05
    POSITIVE LOGITS
    ÏĩεδÏĮν
    0.07
     GUIStyle
    0.07
    oftware
    0.07
    hower
    0.07
    ieur
    0.07
    Å©
    0.07
    noÅĽÄĩ
    0.07
    itty
    0.07
    ¢
    0.07
    vals
    0.07
    Activations Density 0.002%

    No Known Activations