© 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. 74333
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "has," particularly in various tenses and 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
    aits
    -0.07
    endor
    -0.07
    iad
    -0.07
    alet
    -0.07
    mpz
    -0.07
    tube
    -0.07
    luet
    -0.06
    ãĥ¼ãĥĦ
    -0.06
     dela
    -0.06
    emade
    -0.06
    POSITIVE LOGITS
     itself
    0.07
    nu
    0.06
    ermo
    0.06
     Zem
    0.06
    df
    0.06
    eme
    0.06
    uh
    0.06
    aki
    0.06
     be
    0.05
    à§įà¦
    0.05
    Activations Density 0.064%

    No Known Activations