© 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. 80209
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "System."

    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
    olley
    -0.06
     se
    -0.06
    nt
    -0.06
     tube
    -0.06
    kop
    -0.06
     Dante
    -0.06
    ä¾Ľ
    -0.05
    so
    -0.05
     tub
    -0.05
    uber
    -0.05
    POSITIVE LOGITS
    anean
    0.09
    .Collections
    0.08
    CLR
    0.08
    beros
    0.07
    Binder
    0.07
    Ñī
    0.07
     dém
    0.07
    аÑĤелÑĮнÑĭÑħ
    0.07
     ########.
    0.07
    binations
    0.07
    Activations Density 0.001%

    No Known Activations