© 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. 78987
    Prev
    Next
    INDEX
    Explanations

    references to charitable organizations and fundraising efforts

    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
    ield
    -0.06
     Ach
    -0.06
    alty
    -0.06
    gross
    -0.06
     pip
    -0.06
    оÑĢо
    -0.05
    Ymd
    -0.05
    rial
    -0.05
    PEAT
    -0.05
     swingers
    -0.05
    POSITIVE LOGITS
     relief
    0.10
     Relief
    0.09
     direct
    0.08
     immediate
    0.08
    Direct
    0.07
    estar
    0.07
     directly
    0.07
     fund
    0.07
    rella
    0.06
     Direct
    0.06
    Activations Density 0.012%

    No Known Activations