© 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. 81499
    Prev
    Next
    INDEX
    Explanations

    instructions for assembling or packaging items correctly

    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
     differently
    -0.07
     Automatic
    -0.06
    tober
    -0.06
     Visibility
    -0.06
     Alien
    -0.06
     automatic
    -0.06
     wor
    -0.06
    .ensure
    -0.06
     tentative
    -0.06
    venge
    -0.06
    POSITIVE LOGITS
    abin
    0.07
    weit
    0.07
    PU
    0.06
    strand
    0.06
    owski
    0.06
    _PCM
    0.06
    ppt
    0.06
    dden
    0.06
    Dub
    0.06
    erra
    0.06
    Activations Density 0.017%

    No Known Activations