© 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. 54814
    Prev
    Next
    INDEX
    Explanations

    formal documentation or reports

    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
    cke
    -0.06
    akh
    -0.06
    illac
    -0.06
    amburger
    -0.06
     éŁ
    -0.06
     VARIABLE
    -0.06
    ousse
    -0.06
     Pep
    -0.06
    éĽĦ
    -0.06
     brewing
    -0.06
    POSITIVE LOGITS
    aru
    0.07
    arty
    0.07
    lood
    0.06
    520
    0.06
    ReadStream
    0.06
    393
    0.06
    etadata
    0.06
    longleftrightarrow
    0.06
    Ø´ÙĨ
    0.06
    RPC
    0.06
    Activations Density 0.000%

    No Known Activations