© 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. 5627
    Prev
    Next
    INDEX
    Explanations

    URLs and web-related content

    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
    ãģĹãĤĩãģĨ
    -0.07
    idad
    -0.06
    wer
    -0.06
     rebate
    -0.06
    oco
    -0.06
    ä¼
    -0.06
     Cul
    -0.06
    _PIPELINE
    -0.06
    iera
    -0.06
    owers
    -0.05
    POSITIVE LOGITS
    .githubusercontent
    0.07
    strup
    0.06
     CT
    0.06
     Yin
    0.06
     vit
    0.06
    CJK
    0.06
    erç
    0.06
    udy
    0.06
    alama
    0.06
    ptime
    0.06
    Activations Density 0.006%

    No Known Activations