© 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. 3035
    Prev
    Next
    INDEX
    Explanations

    terms related to collections or categories in design and imagery

    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
    alin
    -0.07
    DMA
    -0.07
    entar
    -0.07
    ftar
    -0.06
     '&'
    -0.06
    rahim
    -0.06
     Archer
    -0.06
    brit
    -0.06
    (solution
    -0.06
    ł
    -0.06
    POSITIVE LOGITS
    380
    0.07
    itzer
    0.06
    itz
    0.06
    eneric
    0.06
    Wunused
    0.06
    dera
    0.06
     fark
    0.06
    haar
    0.06
    	Copyright
    0.06
    еви
    0.06
    Activations Density 0.000%

    No Known Activations