© 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. 42792
    Prev
    Next
    INDEX
    Explanations

    occurrences of live events and updates

    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
    arest
    -0.07
     Tarihi
    -0.07
    ajan
    -0.07
    arkin
    -0.07
    AMP
    -0.07
     pur
    -0.07
    .lv
    -0.07
    ampa
    -0.06
    aram
    -0.06
    als
    -0.06
    POSITIVE LOGITS
     US
    0.06
    inas
    0.06
    _firestore
    0.06
    @Spring
    0.06
    -ish
    0.06
     Pac
    0.06
    æĮĩ
    0.05
    보기
    0.05
    PR
    0.05
    nofollow
    0.05
    Activations Density 0.004%

    No Known Activations