© 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. 41435
    Prev
    Next
    INDEX
    Explanations

    references to casinos and gaming regulations

    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
    LOCK
    -0.07
    thood
    -0.07
     Ñĥг
    -0.06
    ify
    -0.06
     ìłĦêµŃ
    -0.06
    ãĥĥãĥī
    -0.06
    åł
    -0.06
    alam
    -0.06
    .Call
    -0.06
    ARAM
    -0.06
    POSITIVE LOGITS
     license
    0.09
     licenses
    0.07
     cle
    0.07
     jurisdiction
    0.07
    licenses
    0.07
    -license
    0.07
    iel
    0.07
     Malta
    0.06
     licence
    0.06
     Jur
    0.06
    Activations Density 0.006%

    No Known Activations