© 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. 94484
    Prev
    Next
    INDEX
    Explanations

    phrases related to project completion and progress

    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
    oom
    -0.06
     Kat
    -0.06
     Jer
    -0.06
    ut
    -0.06
     Ang
    -0.05
    aps
    -0.05
    iv
    -0.05
     society
    -0.05
     Dess
    -0.05
     Ferr
    -0.05
    POSITIVE LOGITS
     final
    0.10
    final
    0.10
    -final
    0.10
     FINAL
    0.09
     finalized
    0.09
    finalize
    0.09
     finishing
    0.08
     finally
    0.08
    FINAL
    0.08
    (final
    0.08
    Activations Density 0.016%

    No Known Activations