© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89601
    Prev
    Next
    INDEX
    Explanations

    references to mud in various contexts

    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
    hood
    -0.07
     addCriterion
    -0.06
    ate
    -0.06
    درس
    -0.06
    dg
    -0.06
    acle
    -0.06
     trừ
    -0.06
    etus
    -0.06
    íĴį
    -0.06
    299
    -0.06
    POSITIVE LOGITS
    INESS
    0.08
    IDGET
    0.08
    ĵåIJį
    0.07
    émon
    0.07
    ied
    0.07
    ÙĪÛĮÙĨ
    0.07
     bucket
    0.07
    iness
    0.07
    -covered
    0.07
    íĨłíĨł
    0.07
    Activations Density 0.011%

    No Known Activations