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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76222
    Prev
    Next
    INDEX
    Explanations

    instances of the word "The" in various 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
    aha
    -0.07
     sl
    -0.06
     locking
    -0.06
    (disposing
    -0.06
    hetic
    -0.05
    /rand
    -0.05
     coll
    -0.05
    mites
    -0.05
    title
    -0.05
    äch
    -0.05
    POSITIVE LOGITS
    amedi
    0.09
     ä¸
    0.08
    cka
    0.07
    à¹Ģà¸ģล
    0.07
    Ã
    0.07
    ylie
    0.07
     withd
    0.07
    #__
    0.07
    мп
    0.07
    divid
    0.07
    Activations Density 0.024%

    No Known Activations