© 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. 103479
    Prev
    Next
    INDEX
    Explanations

    elements related to web or API structure

    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
    oa
    -0.06
     units
    -0.06
    cul
    -0.06
    intr
    -0.06
     rev
    -0.06
     nuts
    -0.05
    ادا
    -0.05
    duct
    -0.05
    oom
    -0.05
    pector
    -0.05
    POSITIVE LOGITS
    ienes
    0.08
    zcze
    0.08
    outu
    0.08
    ubat
    0.08
    elper
    0.08
    òng
    0.07
    ieten
    0.07
     ARGS
    0.07
    enger
    0.07
    anje
    0.07
    Activations Density 0.002%

    No Known Activations