© 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. 5-LLAMASCOPE-RES-131K
    11. 126560
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various 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
    elli
    -0.07
    alt
    -0.06
    oku
    -0.06
    enity
    -0.06
     motive
    -0.06
    ìķĦ
    -0.06
     others
    -0.06
    amber
    -0.05
    LEAR
    -0.05
    lesc
    -0.05
    POSITIVE LOGITS
    iring
    0.07
    isce
    0.07
    oling
    0.07
    izzo
    0.07
    StringRef
    0.07
    inyin
    0.07
    &s
    0.07
    oins
    0.07
    =result
    0.07
    iero
    0.07
    Activations Density 0.009%

    No Known Activations