© 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. 42711
    Prev
    Next
    INDEX
    Explanations

    connections related to collective experience and ownership

    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
    ritt
    -0.07
    ÙĪار
    -0.07
    елен
    -0.07
     ister
    -0.07
    foy
    -0.06
    oval
    -0.06
    625
    -0.06
    è²
    -0.06
     khắc
    -0.06
    unsch
    -0.06
    POSITIVE LOGITS
    BS
    0.07
    nano
    0.07
     verv
    0.07
    oteric
    0.06
    ÄĻż
    0.06
     truth
    0.06
    õi
    0.06
    ponential
    0.06
    alnız
    0.06
     Authorities
    0.06
    Activations Density 0.000%

    No Known Activations