© 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. 17-LLAMASCOPE-RES-131K
    11. 59785
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to awards and recognition in various programs

    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
    cheap
    -0.07
     cheap
    -0.07
     Barg
    -0.06
     sor
    -0.06
    igua
    -0.06
     neither
    -0.06
    Gram
    -0.06
     Gram
    -0.06
    ìĹ´
    -0.06
     Maul
    -0.06
    POSITIVE LOGITS
     rewards
    0.07
    oplan
    0.07
    ìłIJ
    0.07
    ÑĪев
    0.07
    ÑĪиб
    0.07
    ):-
    0.07
    TOOLS
    0.07
     اÙĦأد
    0.07
    simp
    0.07
     tier
    0.07
    Activations Density 0.004%

    No Known Activations