© 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 EvalsExportsAPI 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. 130702
    Prev
    Next
    INDEX
    Explanations

    terms related to Concordia University and its affiliates

    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
    utto
    -0.07
    orial
    -0.07
    ereco
    -0.07
    BJ
    -0.07
    .pub
    -0.07
    urgy
    -0.07
    oons
    -0.06
    outu
    -0.06
    Channels
    -0.06
    earing
    -0.06
    POSITIVE LOGITS
    s
    0.06
     ado
    0.06
    enate
    0.06
    op
    0.06
    озд
    0.06
    ãĥ«ãĥī
    0.06
     conc
    0.06
    ussion
    0.06
    elia
    0.06
    conc
    0.06
    Activations Density 0.016%

    No Known Activations