© 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. 17-LLAMASCOPE-RES-131K
    11. 78221
    Prev
    Next
    INDEX
    Explanations

    phrases related to product durability and longevity

    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
    بÛĮر
    -0.06
    вÑĸлÑĮ
    -0.06
     kite
    -0.06
    oni
    -0.06
    éĤ£ç§į
    -0.06
    è¦
    -0.06
    bern
    -0.06
    itz
    -0.06
    é
    -0.06
    trained
    -0.06
    POSITIVE LOGITS
     WARRANT
    0.08
     years
    0.07
    uire
    0.07
    æĪ·
    0.07
    vestment
    0.07
    ahoma
    0.07
     lifetime
    0.06
    years
    0.06
    reuse
    0.06
    dden
    0.06
    Activations Density 0.007%

    No Known Activations