© 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. 93182
    Prev
    Next
    INDEX
    Explanations

    information related to educational content and guidance around processes or procedures

    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
    ldkf
    -0.07
     âĹĦ
    -0.07
    @nate
    -0.07
    ARGIN
    -0.07
    .kr
    -0.07
    ©©
    -0.07
    ÑģÑĤан
    -0.07
    åŁ
    -0.07
    ắm
    -0.07
    ladu
    -0.07
    POSITIVE LOGITS
     special
    0.09
     examples
    0.08
     associated
    0.08
     typical
    0.07
     recent
    0.07
    toi
    0.07
     how
    0.07
     common
    0.07
     other
    0.07
     types
    0.07
    Activations Density 0.031%

    No Known Activations