© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82473
    Prev
    Next
    INDEX
    Explanations

    articles and descriptive adjectives related to specific objects or experiences

    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
    ogui
    -0.08
    ÏĢÏĮ
    -0.07
    ãĥ¡ãĥ©
    -0.07
    presence
    -0.07
    ìĩ¼
    -0.07
     tầm
    -0.07
    aisal
    -0.07
    herited
    -0.07
    sko
    -0.07
    cased
    -0.07
    POSITIVE LOGITS
     places
    0.10
     location
    0.09
     destination
    0.09
     locations
    0.09
     place
    0.09
     destinations
    0.09
     site
    0.08
    éĤ£éĩĮ
    0.08
     where
    0.08
     sites
    0.07
    Activations Density 0.046%

    No Known Activations