© 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. 30197
    Prev
    Next
    INDEX
    Explanations

    references to political agreements or negotiations

    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
    stag
    -0.09
    ÑĨик
    -0.08
    ãĤĿ
    -0.08
    çĽijåIJ¬é¡µéĿ¢
    -0.08
    Assembly
    -0.08
    itsu
    -0.07
    éĺħ读次æķ°
    -0.07
    оÑĢе
    -0.07
    FILENAME
    -0.07
    íħ
    -0.07
    POSITIVE LOGITS
     permanent
    0.07
     _
    0.07
    0.07
     (
    0.07
     [
    0.06
     Kou
    0.06
     Guar
    0.06
    on
    0.06
     Ban
    0.06
     wol
    0.06
    Activations Density 0.015%

    No Known Activations