© 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. 31261
    Prev
    Next
    INDEX
    Explanations

    numerical data related to testing and performance metrics

    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
    illac
    -0.07
    ãģ¡ãģ¯
    -0.07
    regor
    -0.07
    agna
    -0.07
    ords
    -0.07
     THROW
    -0.07
    égor
    -0.07
    ometown
    -0.07
    ivos
    -0.07
    orsch
    -0.07
    POSITIVE LOGITS
    537
    0.06
     <--
    0.06
    Memory
    0.06
    yo
    0.06
    95
    0.06
     verz
    0.06
    burst
    0.06
    _MEM
    0.06
     proc
    0.06
    опÑĢи
    0.06
    Activations Density 0.003%

    No Known Activations