© 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. 29494
    Prev
    Next
    INDEX
    Explanations

    keywords related to economic and public sector topics

    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
    ampp
    -0.09
     mesel
    -0.08
    poz
    -0.08
    UNDLE
    -0.08
    OLOR
    -0.08
    пÑĢимеÑĢ
    -0.08
    olor
    -0.08
    UNET
    -0.08
    etched
    -0.08
    IRCLE
    -0.07
    POSITIVE LOGITS
     &
    0.07
     clients
    0.06
    alt
    0.06
     M
    0.06
     global
    0.06
     Clients
    0.06
     (
    0.06
     +
    0.06
     connected
    0.06
     Practice
    0.06
    Activations Density 0.004%

    No Known Activations