© 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. 86940
    Prev
    Next
    INDEX
    Explanations

    references to visibility and sight-related concepts

    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
     Gallagher
    -0.07
    ephy
    -0.07
     Sink
    -0.07
    声
    -0.07
    ằ
    -0.07
    loff
    -0.06
    ibs
    -0.06
    illon
    -0.06
    drawer
    -0.06
    ело
    -0.06
    POSITIVE LOGITS
     getWindow
    0.08
     windows
    0.07
    æľ
    0.07
     vision
    0.07
     keen
    0.07
     hood
    0.06
    /view
    0.06
    .instrument
    0.06
    seealso
    0.06
    ãĥ¼ãĥĵ
    0.06
    Activations Density 0.010%

    No Known Activations