© 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. 87731
    Prev
    Next
    INDEX
    Explanations

    numerical values related to dates and years

    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
    erland
    -0.08
    olib
    -0.06
    oux
    -0.06
    |int
    -0.06
    /backend
    -0.06
    ãĥ«ãĥķ
    -0.06
     desar
    -0.06
    /by
    -0.06
    ctors
    -0.06
    tribution
    -0.06
    POSITIVE LOGITS
     tomorrow
    0.07
     previous
    0.06
     futures
    0.06
     fut
    0.06
    åĩĢ
    0.06
     essence
    0.06
     forthcoming
    0.06
     cases
    0.06
     future
    0.06
     Ekon
    0.06
    Activations Density 0.014%

    No Known Activations