© 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. 56056
    Prev
    Next
    INDEX
    Explanations

    timestamps and time-related phrases

    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
    ayer
    -0.06
    inst
    -0.06
    bid
    -0.06
    enties
    -0.06
    vc
    -0.06
    AYER
    -0.06
    resp
    -0.06
    oir
    -0.06
     forall
    -0.06
     Farrell
    -0.06
    POSITIVE LOGITS
     اÙħر
    0.08
    LIKELY
    0.07
     Territory
    0.07
    .scalablytyped
    0.06
     [+
    0.06
     Za
    0.06
    çek
    0.06
    zeigen
    0.06
    .GO
    0.06
    Ñĥз
    0.06
    Activations Density 0.000%

    No Known Activations