© 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. 82269
    Prev
    Next
    INDEX
    Explanations

    elements related to audio quality and experiences in media

    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
    696
    -0.07
    _DDR
    -0.06
    929
    -0.06
     Hicks
    -0.06
    995
    -0.06
    æŁĦ
    -0.05
     Graphic
    -0.05
    req
    -0.05
     bodies
    -0.05
     Participation
    -0.05
    POSITIVE LOGITS
    Menus
    0.07
    Presentation
    0.07
    tere
    0.07
    agements
    0.07
    hed
    0.06
    erner
    0.06
    AffineTransform
    0.06
    rede
    0.06
    uguay
    0.06
    ully
    0.06
    Activations Density 0.001%

    No Known Activations