© 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. 86504
    Prev
    Next
    INDEX
    Explanations

    references to modifications or mods in gaming contexts

    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
     muscle
    -0.06
    ÙģÙĬ
    -0.06
    íį¼
    -0.06
    度
    -0.06
    von
    -0.06
     Wik
    -0.06
    679
    -0.06
    åľŃ
    -0.06
     ac
    -0.06
    eme
    -0.05
    POSITIVE LOGITS
     mod
    0.07
    .mod
    0.07
    entai
    0.07
    addon
    0.07
    dsn
    0.07
    ipar
    0.07
    -wow
    0.07
    -map
    0.06
    )))),
    0.06
    ignum
    0.06
    Activations Density 0.006%

    No Known Activations