© 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. 15-LLAMASCOPE-RES-131K
    11. 87114
    Prev
    Next
    INDEX
    Explanations

    references to measurements and testing protocols in a clinical study

    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
    à¹Ģห
    -0.07
    ÙģاÙĤ
    -0.07
    uden
    -0.06
    uai
    -0.06
    _GB
    -0.06
    ucch
    -0.06
     ÙĪÛĮÚ©ÛĮ
    -0.06
     ãĥ»
    -0.06
    monic
    -0.06
    pn
    -0.06
    POSITIVE LOGITS
    rish
    0.07
    ©
    0.07
    ourke
    0.07
    DBC
    0.07
    _strerror
    0.06
     Norman
    0.06
     ApiException
    0.06
    DataURL
    0.06
    Norm
    0.06
     standardized
    0.06
    Activations Density 0.027%

    No Known Activations