© 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. 75783
    Prev
    Next
    INDEX
    Explanations

    elements of visual and emotional representation in descriptions

    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
    addir
    -0.08
     gezocht
    -0.08
     voks
    -0.07
     zoekt
    -0.07
    hei
    -0.07
    odash
    -0.07
     kale
    -0.07
    à¹īาย
    -0.07
    ambi
    -0.07
     jadx
    -0.06
    POSITIVE LOGITS
    wf
    0.06
     annotation
    0.06
     seem
    0.06
    engl
    0.06
     Propel
    0.06
     Annotation
    0.06
     appear
    0.06
     frozen
    0.05
     perhaps
    0.05
     Alam
    0.05
    Activations Density 0.022%

    No Known Activations