© 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. 95742
    Prev
    Next
    INDEX
    Explanations

    words related to actions or events in a narrative context

    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
    .scalablytyped
    -0.08
    адÑĥ
    -0.08
    说çļĦ
    -0.07
    illis
    -0.07
    ching
    -0.07
    zell
    -0.07
    cherche
    -0.07
    å±±å¸Ĥ
    -0.06
    WEEN
    -0.06
     понима
    -0.06
    POSITIVE LOGITS
    otti
    0.07
    ensburg
    0.06
     took
    0.06
     gave
    0.06
    ipc
    0.06
    itionally
    0.06
     were
    0.06
    inkel
    0.06
     Bottom
    0.06
    ÃŃg
    0.06
    Activations Density 0.018%

    No Known Activations