© 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 EvalsExportsinterp-engineNEWAPI 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. 27326
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names or terms associated with individuals or titles related to food

    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
    bara
    -0.08
    iffin
    -0.07
    á»Ļ
    -0.07
    uden
    -0.07
    ساÙĦ
    -0.07
    _FF
    -0.07
    äºķ
    -0.07
    theon
    -0.06
    BAR
    -0.06
    ald
    -0.06
    POSITIVE LOGITS
    sson
    0.08
    ive
    0.08
    ory
    0.07
    son
    0.07
    ually
    0.07
    ussen
    0.07
    rix
    0.07
    ively
    0.07
    476
    0.07
    zen
    0.07
    Activations Density 0.003%

    No Known Activations