© 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. 92630
    Prev
    Next
    INDEX
    Explanations

    references to films and television specials, particularly around holiday themes and streaming services

    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
    233
    -0.06
     whe
    -0.06
    åħ¥ãĤĬ
    -0.06
     Whe
    -0.06
    _PTR
    -0.06
    /operators
    -0.06
     Sensor
    -0.06
    ensor
    -0.06
    SED
    -0.05
     Gott
    -0.05
    POSITIVE LOGITS
     streaming
    0.08
    flix
    0.07
     stream
    0.07
    -stream
    0.07
     rental
    0.07
     Movies
    0.07
     viewing
    0.07
     ActiveSupport
    0.07
     Viewing
    0.07
     sublicense
    0.07
    Activations Density 0.101%

    No Known Activations