© 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. 4712
    Prev
    Next
    INDEX
    Explanations

    phrases related to signaling and communication systems

    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
    avig
    -0.07
    glob
    -0.06
    ANC
    -0.06
    oÅĻ
    -0.06
     pathways
    -0.06
    robat
    -0.06
     designers
    -0.06
     Laurent
    -0.06
    anium
    -0.06
    con
    -0.06
    POSITIVE LOGITS
    lrt
    0.07
    .MODEL
    0.07
    à¥Ĥà¤Ĥ
    0.07
    gings
    0.07
    InSection
    0.07
    VRT
    0.07
    éĢ¸
    0.07
     pickups
    0.07
    qml
    0.07
    amics
    0.07
    Activations Density 0.001%

    No Known Activations