© 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. 129507
    Prev
    Next
    INDEX
    Explanations

    punctuation and delimiters

    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
    ={"/
    -0.06
     pressure
    -0.06
    öst
    -0.06
    apes
    -0.06
     semi
    -0.06
     fours
    -0.06
     Mint
    -0.06
     **/↵↵
    -0.06
    olk
    -0.06
     dev
    -0.06
    POSITIVE LOGITS
    eyse
    0.08
    emain
    0.07
    uteur
    0.07
    feit
    0.07
    è§
    0.07
    oldem
    0.07
    ãĥ³ãĥĸ
    0.07
    itin
    0.07
    ìļ¸
    0.07
    ayi
    0.06
    Activations Density 0.008%

    No Known Activations