© 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. 39387
    Prev
    Next
    INDEX
    Explanations

    instances of cooperative language and phrases that indicate collaboration or partnerships

    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
    kir
    -0.07
    ê·ľ
    -0.07
     dane
    -0.07
    WB
    -0.07
     straw
    -0.07
    queeze
    -0.07
     Straw
    -0.07
    _mk
    -0.07
     Insecta
    -0.06
    oultry
    -0.06
    POSITIVE LOGITS
     chances
    0.13
    çļĦè¯Ŀ
    0.10
     odds
    0.09
     likelihood
    0.08
    likelihood
    0.08
    å°±ä¼ļ
    0.08
     will
    0.07
    asis
    0.07
     then
    0.07
    ä¼ļ
    0.07
    Activations Density 0.024%

    No Known Activations