© 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. 76841
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" and related forms

    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
    ouz
    -0.07
    ipay
    -0.07
    ëĦIJ
    -0.07
    uche
    -0.07
    olon
    -0.07
    deen
    -0.07
    Ñİ
    -0.07
    âĢ¦↵↵↵
    -0.06
    laden
    -0.06
    byn
    -0.06
    POSITIVE LOGITS
    onio
    0.08
    LLU
    0.07
    BJ
    0.07
    erk
    0.07
    sig
    0.06
    oney
    0.06
     Mint
    0.06
    er
    0.06
    fter
    0.06
    LS
    0.06
    Activations Density 0.004%

    No Known Activations