© 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. 79433
    Prev
    Next
    INDEX
    Explanations

    references to Australian films and theatrical works

    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
     viewing
    -0.07
     Viewing
    -0.07
    olar
    -0.07
    idi
    -0.07
    -sama
    -0.06
    XL
    -0.06
    ìľł
    -0.06
     веÑī
    -0.06
    ervas
    -0.06
    lew
    -0.06
    POSITIVE LOGITS
     setting
    0.11
     characters
    0.10
     settings
    0.10
     Setting
    0.09
     protagonist
    0.09
     scenarios
    0.09
    è¨Ńå®ļ
    0.08
    SETTING
    0.08
     dealing
    0.08
    Setting
    0.08
    Activations Density 0.251%

    No Known Activations