© 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. 70512
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features related to products, particularly those involving mechanical or electronic aspects

    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
    ych
    -0.07
    izik
    -0.07
     ju
    -0.07
    argas
    -0.07
    664
    -0.07
    arga
    -0.07
    lei
    -0.07
    inki
    -0.06
    511
    -0.06
    aben
    -0.06
    POSITIVE LOGITS
    ãĤ¤ãĥ¤
    0.08
     mechanism
    0.07
     option
    0.07
    ertino
    0.06
     feature
    0.06
     Jennings
    0.06
     elim
    0.06
    amework
    0.06
    ICODE
    0.06
     provisions
    0.06
    Activations Density 0.026%

    No Known Activations