© 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. 130895
    Prev
    Next
    INDEX
    Explanations

    terms relating to data, personal versus public contexts, and modernity in discussions

    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
    lek
    -0.07
     klu
    -0.07
    geo
    -0.07
     Vs
    -0.07
    lessly
    -0.06
    ystone
    -0.06
    mul
    -0.06
    urr
    -0.06
     beforeSend
    -0.06
    ÄįnÄĽ
    -0.06
    POSITIVE LOGITS
     alike
    0.19
     worlds
    0.10
     respectively
    0.09
     sides
    0.09
     Worlds
    0.09
     modes
    0.08
     equally
    0.07
     respective
    0.07
     olmak
    0.07
     halves
    0.07
    Activations Density 0.040%

    No Known Activations