© 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. 127316
    Prev
    Next
    INDEX
    Explanations

    fragmented sentences and expressions of outrage

    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
    later
    -0.06
    wart
    -0.06
     coun
    -0.06
    åħ´
    -0.06
    allas
    -0.06
     later
    -0.06
     Oaks
    -0.06
     companion
    -0.06
     còn
    -0.06
     ÑģÑĤол
    -0.06
    POSITIVE LOGITS
    eniable
    0.07
     Management
    0.07
     problem
    0.07
     ç¦
    0.07
    éºĹ
    0.07
    .bz
    0.07
     SOLUTION
    0.07
     Proble
    0.07
     solution
    0.06
    .Management
    0.06
    Activations Density 0.003%

    No Known Activations