© 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. 82701
    Prev
    Next
    INDEX
    Explanations

    mentions of notable individuals or 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
    xdc
    -0.08
    ëł´
    -0.07
    steder
    -0.07
     $č↵
    -0.07
    Ĵáŀ
    -0.07
     ÑģпÑĢави
    -0.07
    ãĥªãĥ³ãĤ°
    -0.07
    ableObject
    -0.07
    .gc
    -0.07
    меÑĤÑĮ
    -0.07
    POSITIVE LOGITS
    uld
    0.06
    ĺIJ
    0.05
     gimm
    0.05
     Sie
    0.05
     Fe
    0.05
    andex
    0.05
     Hamm
    0.05
     manip
    0.05
    modal
    0.05
     Dion
    0.05
    Activations Density 0.000%

    No Known Activations