© 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. 76192
    Prev
    Next
    INDEX
    Explanations

    references to researchers and their contributions

    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
    ãĥ³ãĥĢ
    -0.07
    closure
    -0.06
    úi
    -0.06
    id
    -0.06
    anova
    -0.06
     subjects
    -0.06
    arend
    -0.06
    /LICENSE
    -0.06
     duplex
    -0.06
    airy
    -0.06
    POSITIVE LOGITS
    wick
    0.08
    åĢ«
    0.07
     former
    0.06
     Lem
    0.06
    _dispatcher
    0.06
    transfer
    0.06
    rek
    0.06
    BUFF
    0.06
    маÑĤи
    0.06
    ISED
    0.06
    Activations Density 0.009%

    No Known Activations