© 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. 93104
    Prev
    Next
    INDEX
    Explanations

    references to "pass" or related variations in the context of contests or documentation

    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
    ashes
    -0.06
    ought
    -0.06
    ize
    -0.06
    editary
    -0.06
    itus
    -0.06
    ymous
    -0.06
    ìĥ¤
    -0.06
    atör
    -0.06
    ãģªãģĦ
    -0.06
    Evaluator
    -0.06
    POSITIVE LOGITS
    enger
    0.09
    engers
    0.08
    /pass
    0.08
    (es
    0.08
    ses
    0.07
    .Pass
    0.07
    ler
    0.07
    phrase
    0.07
    ess
    0.07
    arra
    0.07
    Activations Density 0.007%

    No Known Activations