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

    Neuronpedia

    Jacobian LensNEW
    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. 56016
    Prev
    Next
    INDEX
    Explanations

    temporal references, particularly related to days and timeframes

    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
    nock
    -0.07
    ôt
    -0.07
     sécur
    -0.07
    amura
    -0.07
     hete
    -0.06
    LEASE
    -0.06
    ãĥ¼ãĥ©
    -0.06
    istrovstvÃŃ
    -0.06
    éĢļ
    -0.06
    onn
    -0.06
    POSITIVE LOGITS
     or
    0.07
    iol
    0.06
    asz
    0.06
    457
    0.06
     gallon
    0.06
    dds
    0.06
    /start
    0.05
    opia
    0.05
     hopefully
    0.05
    433
    0.05
    Activations Density 0.026%

    No Known Activations