© 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. 117340
    Prev
    Next
    INDEX
    Explanations

    expressions related to production and casting in theatrical 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
     various
    -0.07
     duly
    -0.07
    EMPL
    -0.06
    bara
    -0.06
     Various
    -0.06
    cles
    -0.06
    erland
    -0.06
    oshi
    -0.06
    -parts
    -0.06
    cher
    -0.06
    POSITIVE LOGITS
     именно
    0.11
     instead
    0.10
    è¿Ļä¹Ī
    0.10
     à¤ĩतन
    0.10
    instead
    0.10
     rather
    0.10
    rather
    0.09
    ç«Ł
    0.09
    å¦ĤæѤ
    0.09
     Ñģаме
    0.09
    Activations Density 0.046%

    No Known Activations