© 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 EvalsExportsAPI 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. 78458
    Prev
    Next
    INDEX
    Explanations

    phrases that denote partnerships or collaborations

    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
    nis
    -0.08
    elong
    -0.07
    chn
    -0.07
    коÑĤ
    -0.07
    fono
    -0.07
    uent
    -0.07
    ÏĥÏĩ
    -0.07
    жно
    -0.07
    оба
    -0.07
     quanh
    -0.07
    POSITIVE LOGITS
     others
    0.11
     nhau
    0.10
    others
    0.09
     other
    0.09
     partner
    0.07
     partners
    0.07
     another
    0.07
     local
    0.07
     altri
    0.07
     Others
    0.07
    Activations Density 0.020%

    No Known Activations