© 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. 87531
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration and partnership between organizations

    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
    lear
    -0.06
    TableCell
    -0.06
    rastructure
    -0.06
    orno
    -0.06
     lÃłnh
    -0.06
    resentation
    -0.06
    abbo
    -0.06
    romise
    -0.06
     if
    -0.06
    оза
    -0.06
    POSITIVE LOGITS
     mutual
    0.10
     mutually
    0.08
    ZH
    0.07
    mut
    0.07
    èĬĻ
    0.07
     continue
    0.07
    egral
    0.07
     continued
    0.07
    IRT
    0.07
    ONGO
    0.07
    Activations Density 0.023%

    No Known Activations