© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104511
    Prev
    Next
    INDEX
    Explanations

    references to the Afghan conflict and negotiations

    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
    azel
    -0.08
    çŃĴ
    -0.07
    hardt
    -0.07
    اÙĩر
    -0.07
    (shared
    -0.07
     eldre
    -0.07
    flen
    -0.07
    ENDOR
    -0.07
    .standard
    -0.07
    APON
    -0.06
    POSITIVE LOGITS
     representatives
    0.10
    represent
    0.08
     represented
    0.08
     dialogue
    0.07
     Dialogue
    0.07
     representative
    0.07
     representing
    0.07
     représent
    0.07
     Representatives
    0.07
     represent
    0.06
    Activations Density 0.017%

    No Known Activations