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

    Neuronpedia

    Jacobian LensNEW
    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. 85583
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be" and its related forms 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
    OfSize
    -0.08
    phinx
    -0.08
     Hüs
    -0.08
    ÏĦÏį
    -0.07
    unde
    -0.07
    EMENT
    -0.07
    ERRU
    -0.07
    terra
    -0.07
    mÃŃt
    -0.07
    ardon
    -0.07
    POSITIVE LOGITS
     Bill
    0.07
     Pam
    0.07
    usto
    0.06
    us
    0.06
     Kit
    0.06
     bill
    0.06
     kit
    0.06
    526
    0.06
    浦
    0.06
     randomly
    0.06
    Activations Density 0.012%

    No Known Activations