© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 105720
    Prev
    Next
    INDEX
    Explanations

    references to the entertainment industry, particularly related to independent films and their themes

    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
    ulk
    -0.09
    ennen
    -0.07
    ække
    -0.07
    resse
    -0.07
    nosti
    -0.07
    Ending
    -0.06
    atie
    -0.06
    ¼åIJĪ
    -0.06
    angi
    -0.06
    ær
    -0.06
    POSITIVE LOGITS
    人æīį
    0.07
    éĤ¦
    0.07
     formulas
    0.07
    fec
    0.07
     PARAMETERS
    0.06
     unb
    0.06
     production
    0.06
     formula
    0.06
     box
    0.06
     equation
    0.06
    Activations Density 0.000%

    No Known Activations