© 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. 38251
    Prev
    Next
    INDEX
    Explanations

    questions about acquiring or understanding various topics

    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
    stit
    -0.07
    Ñıж
    -0.06
    azu
    -0.06
    orig
    -0.06
    sid
    -0.06
    enu
    -0.06
    ometr
    -0.06
    itz
    -0.06
    adele
    -0.06
    DITION
    -0.06
    POSITIVE LOGITS
    "nil
    0.07
     Ukra
    0.06
    istrovstvÃŃ
    0.06
     arou
    0.06
    classed
    0.06
     mData
    0.06
    ê°¤
    0.06
     FileMode
    0.06
    ikip
    0.05
    oj
    0.05
    Activations Density 0.025%

    No Known Activations