© 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. 124674
    Prev
    Next
    INDEX
    Explanations

    questions and answers or question-and-answer format in text

    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
    1
    -0.07
     Dont
    -0.07
    C
    -0.06
     Bring
    -0.06
    H
    -0.06
     latter
    -0.06
    N
    -0.06
    3
    -0.06
    2
    -0.06
    0
    -0.06
    POSITIVE LOGITS
    isContained
    0.10
     Ø¢ÛĮا
    0.09
     mastur
    0.09
    (EXPR
    0.09
     tabPage
    0.09
     addCriterion
    0.09
    Ưá»
    0.09
    ãĥ¬ãĥ³
    0.08
    styleType
    0.08
    matchCondition
    0.08
    Activations Density 0.006%

    No Known Activations