© 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. 105385
    Prev
    Next
    INDEX
    Explanations

    expressions of personal connections and social interactions

    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
    pper
    -0.07
    linger
    -0.07
    atz
    -0.06
    unes
    -0.06
    eyse
    -0.06
    etimes
    -0.06
    urm
    -0.06
    ourmet
    -0.06
    adb
    -0.06
    unger
    -0.06
    POSITIVE LOGITS
    Vision
    0.07
    æŁ³
    0.07
     domest
    0.07
    ÃŃk
    0.07
    vat
    0.07
     hvad
    0.06
    λÏİ
    0.06
    ISTA
    0.06
    ÑĢÑĥÑĩ
    0.06
    LEV
    0.06
    Activations Density 0.010%

    No Known Activations