© 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. 62150
    Prev
    Next
    INDEX
    Explanations

    descriptions of performance quality and skill

    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
    eway
    -0.07
    rowsable
    -0.07
    uiltin
    -0.06
     goodness
    -0.06
    ìĸ¸
    -0.06
    are
    -0.06
    .Invariant
    -0.06
    itta
    -0.06
    214
    -0.06
    以
    -0.06
    POSITIVE LOGITS
    gel
    0.07
    rame
    0.07
    ả
    0.07
    ırak
    0.07
    osto
    0.07
    tre
    0.07
    кÑĢаÑĹн
    0.06
    artz
    0.06
    ellation
    0.06
    PTH
    0.06
    Activations Density 0.029%

    No Known Activations