© 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. 16027
    Prev
    Next
    INDEX
    Explanations

    references to organizational roles and procedures

    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
     inn
    -0.06
    Insensitive
    -0.06
    issen
    -0.06
    edm
    -0.06
     Contrib
    -0.06
    .tf
    -0.06
    .ol
    -0.06
    avity
    -0.06
    ancellable
    -0.06
     Broadcast
    -0.06
    POSITIVE LOGITS
     accompany
    0.09
     presence
    0.08
    presence
    0.08
     accompanies
    0.08
     attendance
    0.07
     Presence
    0.07
     accompanying
    0.07
    insky
    0.07
     ØŃضÙĪر
    0.07
     participation
    0.07
    Activations Density 0.015%

    No Known Activations