© 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. 123345
    Prev
    Next
    INDEX
    Explanations

    references to philanthropic efforts and community support

    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
    anik
    -0.07
    cela
    -0.07
    uye
    -0.07
    theid
    -0.07
    undi
    -0.07
    éı
    -0.06
    alles
    -0.06
    cus
    -0.06
    ̣
    -0.06
    cmc
    -0.06
    POSITIVE LOGITS
     requirements
    0.13
     needs
    0.12
     demands
    0.10
    requirements
    0.10
    needs
    0.10
     Needs
    0.09
     Requirements
    0.09
    _requirements
    0.09
     challenge
    0.09
     standards
    0.09
    Activations Density 0.018%

    No Known Activations