© 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. 14669
    Prev
    Next
    INDEX
    Explanations

    terms related to accountability and financial tracking

    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
    ktop
    -0.07
    formed
    -0.07
    qc
    -0.06
    ilt
    -0.06
    ż
    -0.06
    Çİ
    -0.06
    inders
    -0.06
    ormal
    -0.06
    heck
    -0.06
    ilters
    -0.06
    POSITIVE LOGITS
    ably
    0.09
    enance
    0.09
    ants
    0.08
    abilities
    0.08
    edly
    0.08
    erc
    0.08
    _circle
    0.08
    books
    0.07
     toán
    0.07
     rece
    0.07
    Activations Density 0.026%

    No Known Activations