© 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. 2147
    Prev
    Next
    INDEX
    Explanations

    occurrences of titles and roles within film and television

    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
    oud
    -0.08
    太éĥİ
    -0.07
    wart
    -0.06
    oby
    -0.06
    æ°ı
    -0.06
    uder
    -0.06
     current
    -0.06
    NullOr
    -0.06
    ithe
    -0.06
    pite
    -0.06
    POSITIVE LOGITS
     Cousins
    0.07
     Agents
    0.07
    اÙĬØ´
    0.07
    Ø¢Ùħ
    0.07
    ìłķìĿĦ
    0.07
     Bos
    0.07
     mê
    0.06
    ÙĪÛĮÙĦ
    0.06
    ĸī
    0.06
    Ưá»
    0.06
    Activations Density 0.014%

    No Known Activations