© 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. 5373
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership or belonging

    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
    èŀį
    -0.07
     parten
    -0.07
    etting
    -0.07
    essler
    -0.07
    ascus
    -0.07
     peaked
    -0.07
     Mayer
    -0.07
    اشت
    -0.07
    oningen
    -0.07
     predecess
    -0.07
    POSITIVE LOGITS
     equivalent
    0.07
    -wide
    0.07
     standard
    0.06
    357
    0.06
    -local
    0.06
     answer
    0.06
    kept
    0.06
    -standard
    0.06
     only
    0.06
    ol
    0.06
    Activations Density 0.011%

    No Known Activations