© 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. 70466
    Prev
    Next
    INDEX
    Explanations

    words related to combining elements or unity

    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
    ayıp
    -0.07
    claimer
    -0.07
    вед
    -0.07
    åľĪ
    -0.07
     FindObjectOfType
    -0.07
    lei
    -0.07
    etur
    -0.07
    Ø·ØŃ
    -0.07
     norske
    -0.07
    udent
    -0.06
    POSITIVE LOGITS
    義
    0.06
     omit
    0.06
    '
    0.06
    anian
    0.05
     fatt
    0.05
    opens
    0.05
     kids
    0.05
    ละ
    0.05
    mere
    0.05
    æĻ®éĢļ
    0.05
    Activations Density 0.000%

    No Known Activations