© 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. 1720
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the best or most significant experiences

    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
    avl
    -0.07
    sled
    -0.07
    ">//
    -0.07
    زÙĬد
    -0.07
    "is
    -0.07
    ilis
    -0.07
    اÛĮز
    -0.07
    ames
    -0.07
    .LayoutStyle
    -0.06
    ãĥ³ãĥĶ
    -0.06
    POSITIVE LOGITS
     parental
    0.06
    gow
    0.06
    ones
    0.06
    ahren
    0.06
     enterprise
    0.06
     routinely
    0.06
    ownt
    0.06
     existence
    0.06
    IFF
    0.06
     ang
    0.06
    Activations Density 0.005%

    No Known Activations