© 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. 70196
    Prev
    Next
    INDEX
    Explanations

    references to vehicles and their specifications

    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
     DISCLAIM
    -0.08
    imler
    -0.08
     kvin
    -0.07
    adio
    -0.07
    ÎŃÏģ
    -0.07
    ylon
    -0.07
    å©·
    -0.07
    uby
    -0.06
     stol
    -0.06
    ossible
    -0.06
    POSITIVE LOGITS
     unspecified
    0.07
    \xa
    0.06
    âħ
    0.06
     Ober
    0.06
    á»īnh
    0.06
     âĢ¦
    0.05
    âĢª
    0.05
    :;↵
    0.05
    PELL
    0.05
     axe
    0.05
    Activations Density 0.037%

    No Known Activations