© 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. 89843
    Prev
    Next
    INDEX
    Explanations

    key events and announcements related to official meetings and conferences

    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
    .paths
    -0.08
    CEEDED
    -0.07
    иÑĤоÑĢ
    -0.07
    ÑģилÑĮ
    -0.07
    ŀæĢ§
    -0.07
    _REFER
    -0.07
     nuru
    -0.07
    ยะ
    -0.07
    迪
    -0.07
    ROKE
    -0.07
    POSITIVE LOGITS
     will
    0.09
    will
    0.07
    0.07
     followed
    0.06
     press
    0.06
    :
    0.06
     brief
    0.06
     public
    0.06
    rift
    0.06
     briefing
    0.06
    Activations Density 0.004%

    No Known Activations