© 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. 39067
    Prev
    Next
    INDEX
    Explanations

    references to sources or citations within a text

    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
    abei
    -0.08
    cone
    -0.07
    590
    -0.07
    rej
    -0.07
    zioni
    -0.06
    aggio
    -0.06
    crete
    -0.06
    iid
    -0.06
    ête
    -0.06
    abant
    -0.06
    POSITIVE LOGITS
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.07
     ActionTypes
    0.07
    Ïģία
    0.06
     Ders
    0.06
    .scalablytyped
    0.06
     kapit
    0.06
    /Area
    0.06
    Mage
    0.06
    HasBeenSet
    0.06
    ราà¸Ĭ
    0.06
    Activations Density 0.006%

    No Known Activations