© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles

    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
    áž
    -0.06
    apo
    -0.06
    iers
    -0.06
    áty
    -0.06
    ASHBOARD
    -0.06
     def
    -0.06
    EEP
    -0.06
    idel
    -0.06
    illa
    -0.06
    ural
    -0.06
    POSITIVE LOGITS
     wiki
    0.07
     hann
    0.07
    ì¢Į
    0.07
     Wiki
    0.06
     mour
    0.06
    lech
    0.06
    .commons
    0.06
    emb
    0.06
    fter
    0.06
    wiki
    0.06
    Activations Density 0.028%

    No Known Activations