© 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. 107572
    Prev
    Next
    INDEX
    Explanations

    licensing terms related to Creative Commons

    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
    asan
    -0.07
    -lang
    -0.06
    stinian
    -0.06
    HCI
    -0.06
    exampleInput
    -0.06
    nett
    -0.06
    hua
    -0.06
    /cpp
    -0.06
    itag
    -0.06
    ÐĿÐĺ
    -0.06
    POSITIVE LOGITS
    /lic
    0.07
    /licenses
    0.07
    شار
    0.06
    ÑĬ
    0.06
    rames
    0.06
     Hoy
    0.06
    ائب
    0.06
    /devices
    0.06
    icers
    0.06
    uess
    0.06
    Activations Density 0.004%

    No Known Activations