© 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 EvalsExportsAPI 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. 130375
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their roles in acting or modeling 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
     Columbus
    -0.06
    èĬĿ
    -0.06
    arias
    -0.06
    aku
    -0.06
    omid
    -0.06
    anka
    -0.06
    itat
    -0.06
    ilia
    -0.06
    linik
    -0.06
     lut
    -0.06
    POSITIVE LOGITS
     Elijah
    0.09
    lijah
    0.08
    wald
    0.06
    borough
    0.06
     Osborne
    0.06
     bordel
    0.06
     Liver
    0.06
     Aç
    0.06
     contraction
    0.06
    Liver
    0.06
    Activations Density 0.002%

    No Known Activations