© 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. 125041
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and definitions related to graphs

    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
    į°
    -0.07
    imiter
    -0.07
    ooter
    -0.07
    orton
    -0.07
    cale
    -0.07
    ÄĽÅ¾
    -0.06
    öst
    -0.06
    ystate
    -0.06
    uffers
    -0.06
    iasi
    -0.06
    POSITIVE LOGITS
    åľ
    0.07
    lya
    0.06
    ynamo
    0.06
     *</
    0.06
     Pon
    0.06
     Kou
    0.06
    ureka
    0.06
    bis
    0.06
    agma
    0.06
     bon
    0.06
    Activations Density 0.043%

    No Known Activations