© 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. 14526
    Prev
    Next
    INDEX
    Explanations

    references to vehicles and their associated terms

    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
    622
    -0.08
    readcr
    -0.07
    alon
    -0.07
    _Static
    -0.07
    .mm
    -0.07
    entar
    -0.07
    entin
    -0.06
    resh
    -0.06
    azor
    -0.06
     cour
    -0.06
    POSITIVE LOGITS
     surre
    0.06
     old
    0.06
     Ingram
    0.06
    haar
    0.06
     troop
    0.06
     pict
    0.06
    avad
    0.06
     Tro
    0.05
     Removal
    0.05
     unwanted
    0.05
    Activations Density 0.001%

    No Known Activations