© 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. 63151
    Prev
    Next
    INDEX
    Explanations

    timestamps and formatting related to date and time

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     ones
    -0.08
    PMC
    -0.07
    sono
    -0.06
     even
    -0.06
     Neighborhood
    -0.06
    ħį
    -0.06
     INLINE
    -0.06
     cast
    -0.06
    ewe
    -0.05
     micro
    -0.05
    POSITIVE LOGITS
    /////////////////////////////////////////////////////////////////////////////↵
    0.07
    ìĪł
    0.07
    nia
    0.07
    ubb
    0.07
    uxt
    0.07
     vá»ĭ
    0.07
    indow
    0.07
    ufs
    0.06
    HEEL
    0.06
    اÙī
    0.06
    Activations Density 0.006%

    No Known Activations