© 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. 38567
    Prev
    Next
    INDEX
    Explanations

    references to levels or floors in a building

    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
    Ñģлед
    -0.07
     ank
    -0.07
     BOTTOM
    -0.06
     uÄŁ
    -0.06
     lá»±c
    -0.06
    eut
    -0.06
     Bottom
    -0.06
     bottom
    -0.06
    ORE
    -0.06
    isci
    -0.06
    POSITIVE LOGITS
    -level
    0.08
     level
    0.07
    aura
    0.07
    صت
    0.06
    以ä¸Ĭ
    0.06
    -Level
    0.06
    ActionCreators
    0.06
     seeds
    0.06
    odont
    0.06
    iyet
    0.06
    Activations Density 0.007%

    No Known Activations