© 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. 85215
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to be" indicating states or conditions

    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
    maj
    -0.07
    çľī
    -0.06
    isoft
    -0.06
    zes
    -0.06
    stal
    -0.06
    .nlm
    -0.06
    anj
    -0.06
    inis
    -0.06
    üsü
    -0.06
    æĢ
    -0.06
    POSITIVE LOGITS
    /Dk
    0.07
    iece
    0.06
     quot
    0.06
     confident
    0.06
    all
    0.06
     confidence
    0.06
     plá
    0.06
    thal
    0.06
     sorry
    0.06
    ãĥĥãĥī
    0.06
    Activations Density 0.023%

    No Known Activations