© 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. 87566
    Prev
    Next
    INDEX
    Explanations

    terms related to software and its applications in different contexts

    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
     заклад
    -0.07
    _faces
    -0.06
     {{--<
    -0.06
    \grid
    -0.06
    Advertisement
    -0.06
    ासन
    -0.06
    anner
    -0.06
    acl
    -0.06
    itmap
    -0.06
    Ãłn
    -0.06
    POSITIVE LOGITS
     such
    0.08
     include
    0.07
     including
    0.07
    such
    0.07
    iment
    0.07
     ÑĤакие
    0.06
    :
    0.06
     ÑĤакиÑħ
    0.06
     SUCH
    0.06
    including
    0.06
    Activations Density 0.048%

    No Known Activations