© 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. 40841
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers or cautionary statements related to investments

    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
    zman
    -0.07
    hon
    -0.07
    zs
    -0.06
    nar
    -0.06
    anne
    -0.06
    æĪ
    -0.06
     OMAP
    -0.06
     Harding
    -0.06
    aises
    -0.06
    irket
    -0.06
    POSITIVE LOGITS
    tw
    0.06
    ries
    0.06
    adows
    0.06
    /browse
    0.06
    /Foundation
    0.06
     kla
    0.06
     forgotten
    0.06
    ActionCreators
    0.06
    аÑı
    0.05
    ãĤ¤ãĤ¯
    0.05
    Activations Density 0.004%

    No Known Activations