© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95530
    Prev
    Next
    INDEX
    Explanations

    references to bracelets and wristbands

    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
    hic
    -0.08
    burgh
    -0.08
     ÐĿаз
    -0.07
    asca
    -0.07
    Ậ
    -0.07
    thon
    -0.07
    Latch
    -0.07
    /original
    -0.07
    มหาà¸Ļà¸Ħร
    -0.07
     ört
    -0.07
    POSITIVE LOGITS
    shaw
    0.06
     lucky
    0.06
    Å
    0.06
    oundary
    0.06
    ordon
    0.06
    ty
    0.06
    863
    0.06
    simp
    0.06
     Horror
    0.05
     band
    0.05
    Activations Density 0.002%

    No Known Activations