© 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. 14323
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities

    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
    erdem
    -0.08
    seau
    -0.07
    strt
    -0.07
    eyen
    -0.07
    á»ijn
    -0.07
    bÄĽh
    -0.06
    edl
    -0.06
    anko
    -0.06
    isse
    -0.06
    -END
    -0.06
    POSITIVE LOGITS
    ReuseIdentifier
    0.06
    pei
    0.06
     Sur
    0.06
     sur
    0.06
    oto
    0.06
    abb
    0.06
    QRS
    0.06
    asto
    0.06
    atto
    0.06
    bout
    0.06
    Activations Density 0.007%

    No Known Activations