© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89495
    Prev
    Next
    INDEX
    Explanations

    references to personal and professional experiences 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
    æĪĸèĢħ
    -0.10
     or
    -0.09
     или
    -0.08
     æĪĸ
    -0.08
    	and
    -0.08
    æĪĸ
    -0.08
    มà¸ķ
    -0.08
     instead
    -0.07
     hoặc
    -0.07
    instead
    -0.07
    POSITIVE LOGITS
     alike
    0.22
     respectively
    0.12
     too
    0.11
    too
    0.10
     ÑĤоже
    0.09
     depending
    0.08
     ones
    0.07
     whichever
    0.07
    respect
    0.07
     Too
    0.07
    Activations Density 0.080%

    No Known Activations