© 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. 15-LLAMASCOPE-RES-131K
    11. 87794
    Prev
    Next
    INDEX
    Explanations

    instances of company names and service references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Business or organization names, typically appearing at the end of a proper noun phrase that describes their function or service type.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     near
    -0.06
    ãĥ§
    -0.06
     reportedly
    -0.06
    owo
    -0.06
     Bliss
    -0.06
     Mas
    -0.05
    observer
    -0.05
    hydr
    -0.05
     meanwhile
    -0.05
    stadt
    -0.05
    POSITIVE LOGITS
    alach
    0.09
     /*č↵
    0.08
    wdx
    0.07
    ASI
    0.07
    ÅĻez
    0.07
     grunt
    0.07
    Vu
    0.07
    -SA
    0.07
    æľīéĻIJ
    0.07
     abych
    0.07
    Activations Density 0.025%

    No Known Activations