© 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. 128222
    Prev
    Next
    INDEX
    Explanations

    references to features and functionalities of technology or software

    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
    ÑĪÑĥ
    -0.09
    ugi
    -0.09
    شتÙĩ
    -0.07
    åµ
    -0.07
     Ñĥгод
    -0.07
    abwe
    -0.07
    urar
    -0.07
     nuôi
    -0.07
    _SPI
    -0.07
    ATAR
    -0.07
    POSITIVE LOGITS
     feature
    0.14
    feature
    0.11
     Feature
    0.10
     option
    0.09
     ability
    0.09
     mode
    0.09
    Feature
    0.09
     features
    0.08
     function
    0.08
    -feature
    0.08
    Activations Density 0.024%

    No Known Activations