© 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. 73801
    Prev
    Next
    INDEX
    Explanations

    events and matchups in competitive contexts

    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
    -UA
    -0.08
    holm
    -0.07
    TestFixture
    -0.07
    arcer
    -0.07
    readcrumbs
    -0.07
    ibel
    -0.07
    arbon
    -0.07
    ettes
    -0.06
    eneg
    -0.06
    OperationException
    -0.06
    POSITIVE LOGITS
     hometown
    0.06
    _RSA
    0.06
    agram
    0.06
    ermann
    0.05
     sacr
    0.05
     paras
    0.05
     vita
    0.05
    ä¼´
    0.05
     mÃŃstnÃŃ
    0.05
    LOY
    0.05
    Activations Density 0.001%

    No Known Activations