© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 2904
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks used in the text

    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
    illez
    -0.07
    ,
    -0.07
     as
    -0.06
    -at
    -0.06
     Jan
    -0.06
    rij
    -0.06
     Candy
    -0.06
     people
    -0.06
     folk
    -0.06
    .
    -0.06
    POSITIVE LOGITS
    ernet
    0.07
    ãĥĥãĥģ
    0.07
    rane
    0.07
    #
    0.07
    ["+
    0.07
     traps
    0.07
    ÏĦή
    0.07
    .Ultra
    0.07
    २०
    0.07
    avors
    0.06
    Activations Density 0.000%

    No Known Activations