© 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. 127253
    Prev
    Next
    INDEX
    Explanations

    terms related to financial allocations and funding decisions

    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
    igham
    -0.06
     or
    -0.06
    osta
    -0.06
    omid
    -0.06
     statistics
    -0.06
     regulation
    -0.05
    emark
    -0.05
     software
    -0.05
     spontaneously
    -0.05
     forged
    -0.05
    POSITIVE LOGITS
    avaÅŁ
    0.09
    ìļ´ëį°
    0.08
    ieri
    0.08
    letic
    0.07
    SSERT
    0.07
    ceptors
    0.07
    GENCY
    0.07
     поÑĪ
    0.07
    formula
    0.07
     Wrest
    0.07
    Activations Density 0.009%

    No Known Activations