© 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. 15-LLAMASCOPE-RES-131K
    11. 88289
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration and partnership

    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
    aldi
    -0.07
    chu
    -0.07
     sublic
    -0.07
    iras
    -0.06
     fier
    -0.06
    _stdio
    -0.06
    ÑĢÑıд
    -0.06
    ÙĨÙĬØ©
    -0.06
    κε
    -0.06
     traj
    -0.06
    POSITIVE LOGITS
    ivre
    0.07
    ohn
    0.06
     approach
    0.06
    OCUS
    0.06
    resi
    0.06
    chez
    0.06
     Schwartz
    0.06
    icher
    0.06
    ãĤ¹ãĤ³
    0.06
    .cloudflare
    0.06
    Activations Density 0.022%

    No Known Activations