© 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 EvalsExportsAPI 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. 106506
    Prev
    Next
    INDEX
    Explanations

    references to government actions and official statements

    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
     αδ
    -0.07
    .sal
    -0.06
    erspective
    -0.06
    oll
    -0.06
     xin
    -0.06
     tô
    -0.06
    -Version
    -0.06
     Antar
    -0.06
    è¿İ
    -0.06
    _ISR
    -0.06
    POSITIVE LOGITS
     personally
    0.11
     ÙģرÙħÙĪد
    0.08
     Personally
    0.08
     himself
    0.07
     Affero
    0.07
     Consolid
    0.07
     orders
    0.07
    orders
    0.07
     insp
    0.07
     personal
    0.06
    Activations Density 0.037%

    No Known Activations