© 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. 9-LLAMASCOPE-RES-131K
    11. 97385
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers related to creative works, particularly albums and novels

    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
    ILING
    -0.06
     toll
    -0.06
    285
    -0.05
    iling
    -0.05
    286
    -0.05
     consum
    -0.05
     deg
    -0.05
     Toll
    -0.05
    ávánÃŃ
    -0.05
    ucket
    -0.05
    POSITIVE LOGITS
    ahun
    0.07
    .exc
    0.07
    .scalablytyped
    0.07
    Pocket
    0.07
    parseFloat
    0.07
    ROC
    0.07
    ron
    0.07
    eyse
    0.07
    isu
    0.07
    Compact
    0.07
    Activations Density 0.006%

    No Known Activations