© 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. 126030
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" and their 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
    otre
    -0.08
    ience
    -0.08
    iba
    -0.07
    atoire
    -0.07
    quia
    -0.07
    illac
    -0.07
    icher
    -0.07
    Ñħа
    -0.07
    bruar
    -0.07
     åĨĨ
    -0.07
    POSITIVE LOGITS
    573
    0.07
    egan
    0.06
     simultaneously
    0.06
    have
    0.06
     elected
    0.06
     domic
    0.06
     active
    0.05
    572
    0.05
    friend
    0.05
    771
    0.05
    Activations Density 0.028%

    No Known Activations