© 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 EvalsExportsinterp-engineNEWAPI 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. 104660
    Prev
    Next
    INDEX
    Explanations

    instances of transitional phrases that suggest a sequence of events

    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
    enheim
    -0.07
    addir
    -0.06
     Libert
    -0.06
    lix
    -0.06
     Firstly
    -0.06
    aris
    -0.06
    .RunWith
    -0.06
    asher
    -0.06
    mond
    -0.06
     dipping
    -0.06
    POSITIVE LOGITS
     then
    0.17
     finally
    0.15
     final
    0.14
     THEN
    0.13
     Finally
    0.13
     Then
    0.13
    then
    0.13
    Then
    0.13
    finally
    0.13
    Finally
    0.12
    Activations Density 0.022%

    No Known Activations