© 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. 15933
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" along with mentions of research, practical solutions, or legislative contexts

    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
    ICI
    -0.08
    èm
    -0.07
    èĢ
    -0.07
    á»Ļng
    -0.07
    Mappings
    -0.06
     бед
    -0.06
    otros
    -0.06
    uffles
    -0.06
     SAME
    -0.06
    alse
    -0.06
    POSITIVE LOGITS
     role
    0.09
     how
    0.08
     anatomy
    0.08
     reasons
    0.07
     roles
    0.07
     ways
    0.07
     causes
    0.07
     why
    0.07
     history
    0.07
    how
    0.07
    Activations Density 0.038%

    No Known Activations