© 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. 108592
    Prev
    Next
    INDEX
    Explanations

    phrases related to explanation and comprehension in scientific 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
     TObject
    -0.06
    hn
    -0.06
     fares
    -0.06
     Schneider
    -0.06
    å¥Ĺ
    -0.06
     Fare
    -0.06
     Sunrise
    -0.06
    åĨł
    -0.06
     Grimm
    -0.06
    _srv
    -0.06
    POSITIVE LOGITS
     observed
    0.13
     why
    0.11
     phenomena
    0.10
     phenomenon
    0.10
     observations
    0.09
    obs
    0.09
    why
    0.09
    observations
    0.09
    为ä»Ģä¹Ī
    0.09
    одо
    0.08
    Activations Density 0.045%

    No Known Activations