© 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. 5709
    Prev
    Next
    INDEX
    Explanations

    tips and advice for practical problem-solving

    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
     because
    -0.06
    because
    -0.06
     able
    -0.06
    bir
    -0.05
     complet
    -0.05
     Moh
    -0.05
     litter
    -0.05
     dow
    -0.05
     Metropolitan
    -0.05
    gam
    -0.05
    POSITIVE LOGITS
     yourself
    0.09
     yourselves
    0.08
     tip
    0.08
     your
    0.08
    ëĿ¼íĶ¼
    0.07
    your
    0.07
    urovision
    0.07
     YOUR
    0.07
    efa
    0.07
    ä½łçļĦ
    0.07
    Activations Density 0.041%

    No Known Activations