© 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. 2160
    Prev
    Next
    INDEX
    Explanations

    content related to recommendations and guidelines from authoritative organizations

    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
    ella
    -0.07
    ollapsed
    -0.07
    .jms
    -0.07
    аÑĢам
    -0.07
    jeme
    -0.07
    cctor
    -0.07
     LENG
    -0.07
    haf
    -0.07
    ensa
    -0.07
    uese
    -0.07
    POSITIVE LOGITS
     UK
    0.07
     parl
    0.06
     European
    0.06
    aits
    0.06
    èĮ
    0.06
     UNESCO
    0.06
     Commission
    0.06
     research
    0.06
     report
    0.06
     recent
    0.06
    Activations Density 0.071%

    No Known Activations