© 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. 62341
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of visual media and machinery, notably "Star Wars," graphics, and various types of crushers

    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
    rary
    -0.08
    anke
    -0.07
    egment
    -0.07
    reon
    -0.07
    ickle
    -0.07
    ahun
    -0.07
    leo
    -0.07
    ece
    -0.06
    ayah
    -0.06
    aland
    -0.06
    POSITIVE LOGITS
    anova
    0.07
     Epstein
    0.06
    oster
    0.06
    698
    0.06
    870
    0.06
    ç½
    0.05
     Stein
    0.05
    atrix
    0.05
    LC
    0.05
     Cyr
    0.05
    Activations Density 0.012%

    No Known Activations