© 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. 40933
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols 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
     parl
    -0.06
     Traditional
    -0.06
    ect
    -0.06
     Shutterstock
    -0.06
    pectives
    -0.06
     Beck
    -0.06
    BootApplication
    -0.06
    lier
    -0.05
     Warn
    -0.05
    aptive
    -0.05
    POSITIVE LOGITS
    odash
    0.08
    boo
    0.08
    itle
    0.08
     genu
    0.07
    eron
    0.07
    ollapse
    0.07
    ÑĢок
    0.07
     hinter
    0.07
    iyan
    0.07
    atum
    0.07
    Activations Density 0.010%

    No Known Activations