© 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. 26728
    Prev
    Next
    INDEX
    Explanations

    structural elements and classifications within text

    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
    usher
    -0.07
    맥
    -0.07
    etto
    -0.07
    ymax
    -0.07
    positor
    -0.06
    StateException
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
     emp
    -0.06
    chants
    -0.06
    lesi
    -0.06
    POSITIVE LOGITS
    tober
    0.06
    æķ´
    0.06
    ategorie
    0.06
     ÙħÙĪارد
    0.06
    agher
    0.06
    .ServiceModel
    0.06
    atz
    0.06
     categories
    0.06
     category
    0.06
    category
    0.05
    Activations Density 0.054%

    No Known Activations