© 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. 4908
    Prev
    Next
    INDEX
    Explanations

    terms related to espionage and spying

    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
    izer
    -0.09
    imers
    -0.08
    quan
    -0.08
    aires
    -0.08
    oit
    -0.07
    ioned
    -0.07
    lam
    -0.07
    serter
    -0.07
    imes
    -0.07
    bred
    -0.07
    POSITIVE LOGITS
    glass
    0.08
    -fi
    0.07
    ernet
    0.07
    bubble
    0.07
    gram
    0.07
    ãĤ·ãĥ¼
    0.06
    goo
    0.06
     objc
    0.06
    optic
    0.06
    ur
    0.06
    Activations Density 0.005%

    No Known Activations