© 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. 17-LLAMASCOPE-RES-131K
    11. 105656
    Prev
    Next
    INDEX
    Explanations

    phrases that express common idiomatic expressions or clichés related to problems or challenges

    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
    w
    -0.06
     quasi
    -0.06
     Bark
    -0.06
    ARIO
    -0.06
    erais
    -0.05
     neut
    -0.05
     mainly
    -0.05
     gross
    -0.05
     obvious
    -0.05
     grosse
    -0.05
    POSITIVE LOGITS
    mere
    0.10
    simple
    0.07
    blade
    0.07
     simple
    0.07
    egin
    0.07
    ç®Ģåįķ
    0.07
    pliant
    0.07
    اÙĦÛĮ
    0.07
    usch
    0.07
     tiny
    0.07
    Activations Density 0.025%

    No Known Activations