© 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. 54241
    Prev
    Next
    INDEX
    Explanations

    references to unsuccessful attempts or actions

    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
    Ậ
    -0.08
    eah
    -0.08
    sembles
    -0.08
    forder
    -0.08
    erable
    -0.08
    zeich
    -0.07
    oxel
    -0.07
    \Id
    -0.07
    taire
    -0.07
    .MixedReality
    -0.07
    POSITIVE LOGITS
     attempt
    0.19
     attempts
    0.17
    attempt
    0.15
     Attempt
    0.14
     attempted
    0.14
    Attempt
    0.13
     Attempts
    0.13
     attempting
    0.13
     tries
    0.12
     try
    0.11
    Activations Density 0.018%

    No Known Activations