© 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. 83207
    Prev
    Next
    INDEX
    Explanations

    references to endorsements or approvals from different entities

    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
     TestUtils
    -0.07
    atat
    -0.07
    ayne
    -0.06
    æŁ»
    -0.06
     fri
    -0.06
    atore
    -0.06
    Redux
    -0.06
    ÙıÙĪا
    -0.06
    ardi
    -0.06
     Inherits
    -0.06
    POSITIVE LOGITS
    INCT
    0.07
    662
    0.06
    Å¡em
    0.06
    eyle
    0.06
     Hess
    0.06
    ONTAL
    0.06
    createFrom
    0.06
     Äijá»ģ
    0.06
    ilateral
    0.06
    öt
    0.06
    Activations Density 0.000%

    No Known Activations