© 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. 55087
    Prev
    Next
    INDEX
    Explanations

    various forms of conditional agreements and financial transactions

    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
    insi
    -0.08
    ROKE
    -0.08
    obi
    -0.07
    arna
    -0.07
    kube
    -0.07
     ActionResult
    -0.07
    IEW
    -0.07
    pard
    -0.07
    Lean
    -0.06
    ÑĤоÑĩ
    -0.06
    POSITIVE LOGITS
     themselves
    0.08
    0.07
     us
    0.07
    CB
    0.06
     their
    0.06
     risk
    0.06
     pl
    0.06
     offer
    0.06
    RTL
    0.06
     work
    0.05
    Activations Density 0.034%

    No Known Activations