© 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. 40481
    Prev
    Next
    INDEX
    Explanations

    references to ratings and reviews of media, particularly books and films

    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
    ìĩ
    -0.07
    ç¸
    -0.07
    ÃŃst
    -0.07
    ercial
    -0.07
    ãĤ¦ãĥĪ
    -0.07
    _TW
    -0.06
    åĪº
    -0.06
    elf
    -0.06
    leh
    -0.06
    plode
    -0.06
    POSITIVE LOGITS
    reviews
    0.08
     rating
    0.08
     reviews
    0.07
    rating
    0.07
     ratings
    0.07
    -rating
    0.07
    Reviews
    0.07
    å¦Ļ
    0.06
     Reviews
    0.06
    ÑĢей
    0.06
    Activations Density 0.004%

    No Known Activations