© 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. 15-LLAMASCOPE-RES-131K
    11. 479
    Prev
    Next
    INDEX
    Explanations

    determinations related to environmental factors and specific actions

    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
    oyer
    -0.08
    ajo
    -0.07
    legg
    -0.07
    ÅŁÄ±
    -0.07
    opsy
    -0.07
    allen
    -0.07
    etooth
    -0.07
    Å¡ÃŃ
    -0.07
    ãĤ«ãĥ«
    -0.07
    þ
    -0.07
    POSITIVE LOGITS
    divid
    0.06
     compartments
    0.06
     inherited
    0.06
     Commercial
    0.06
    /animate
    0.06
    NSInteger
    0.06
     Supplement
    0.06
    dom
    0.06
    ledo
    0.06
    iger
    0.06
    Activations Density 0.000%

    No Known Activations