© 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. 86778
    Prev
    Next
    INDEX
    Explanations

    technical terms related to immunology

    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
    v
    -0.07
    ui
    -0.06
    arez
    -0.06
    apl
    -0.06
    hell
    -0.06
    omb
    -0.06
    zn
    -0.06
     targeting
    -0.06
     perv
    -0.05
    abaj
    -0.05
    POSITIVE LOGITS
    iminal
    0.08
    mitter
    0.07
     Nicholson
    0.07
    erties
    0.07
    oggler
    0.07
     ì²ĺ
    0.07
    åŀ
    0.07
    oins
    0.07
    avad
    0.07
    ãĥ¼ãĥķ
    0.07
    Activations Density 0.000%

    No Known Activations