© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86522
    Prev
    Next
    INDEX
    Explanations

    details regarding volunteer and community engagement activities

    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
    istrovstvÃŃ
    -0.08
    ulur
    -0.08
    ÙĪÛĮØ´
    -0.08
    makt
    -0.08
    .scalablytyped
    -0.08
    racat
    -0.08
    AtA
    -0.07
     Kasım
    -0.07
    uards
    -0.07
     Angeles
    -0.07
    POSITIVE LOGITS
     etc
    0.08
     set
    0.07
    etc
    0.07
     prob
    0.06
     supplement
    0.06
     use
    0.06
     enc
    0.06
     transition
    0.06
     bore
    0.06
     hosts
    0.06
    Activations Density 0.050%

    No Known Activations