© 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. 126460
    Prev
    Next
    INDEX
    Explanations

    monetary values and pricing information related to services

    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
     hotel
    -0.07
    ERA
    -0.06
    кÑģ
    -0.06
     Versions
    -0.06
     versions
    -0.06
     blot
    -0.05
     Journey
    -0.05
     site
    -0.05
    udo
    -0.05
     Hotel
    -0.05
    POSITIVE LOGITS
    privation
    0.07
    :UIAlert
    0.07
    /XMLSchema
    0.07
    sez
    0.07
    é¾
    0.07
    fers
    0.07
    еÑĢеж
    0.06
    лиÑĤелÑĮ
    0.06
    _clr
    0.06
    MATRIX
    0.06
    Activations Density 0.004%

    No Known Activations