© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3616
    Prev
    Next
    INDEX
    Explanations

    capital letters at the beginning of key terms or headings

    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
    ãģ£ãģı
    -0.08
    ught
    -0.07
    ouncer
    -0.07
    eltas
    -0.07
    pher
    -0.07
    ched
    -0.07
    ecs
    -0.07
    aviest
    -0.07
    compat
    -0.06
    udge
    -0.06
    POSITIVE LOGITS
    onen
    0.08
    orem
    0.08
    oret
    0.08
    etheless
    0.08
    while
    0.07
    çħ§
    0.07
    iming
    0.06
     soon
    0.06
    å½ĵ
    0.06
    aru
    0.06
    Activations Density 0.032%

    No Known Activations