© 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. 57258
    Prev
    Next
    INDEX
    Explanations

    references to organizations, institutions, and their employees

    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
    /details
    -0.07
    olley
    -0.06
    venes
    -0.06
     Franklin
    -0.06
    eting
    -0.06
    \controllers
    -0.06
    uft
    -0.06
     item
    -0.06
    agas
    -0.06
    /controllers
    -0.06
    POSITIVE LOGITS
    -wide
    0.10
    .scalablytyped
    0.09
    wide
    0.09
    ernals
    0.08
    AdapterManager
    0.07
    GuidId
    0.07
     TestUtils
    0.07
    ymbol
    0.07
     DBHelper
    0.07
    CallableWrapper
    0.07
    Activations Density 0.044%

    No Known Activations