© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 93107
    Prev
    Next
    INDEX
    Explanations

    active phrases that indicate capability or possibility

    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
    ventus
    -0.10
    mamak
    -0.09
    ersh
    -0.08
    .scalablytyped
    -0.08
     ведÑĮ
    -0.08
    CORE
    -0.08
    걸
    -0.08
    -transitional
    -0.08
    ropri
    -0.07
    indr
    -0.07
    POSITIVE LOGITS
     potentially
    0.07
     effectively
    0.06
     newIndex
    0.06
     must
    0.06
     less
    0.06
     instead
    0.06
     no
    0.06
     either
    0.06
     sooner
    0.06
     Ta
    0.05
    Activations Density 0.056%

    No Known Activations