Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43704
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    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
     seguint
    -0.07
    OffsetTable
    -0.06
    leich
    -0.06
     kür
    -0.06
    BoxLayout
    -0.06
    igham
    -0.06
    ayload
    -0.06
    SizeMode
    -0.06
     siguiente
    -0.06
    omentum
    -0.06
    POSITIVE LOGITS
     inception
    0.16
     dawn
    0.15
     turn
    0.15
     advent
    0.15
     beginning
    0.14
     start
    0.14
     days
    0.13
     invention
    0.13
     onset
    0.13
     arrival
    0.13
    Activations Density 0.039%

    No Known Activations