© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106368
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and notation related to set theory and vector spaces

    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
    olia
    -0.07
    MMdd
    -0.07
    .Îł
    -0.06
    коÑĢиÑģÑĤ
    -0.06
    ured
    -0.06
     urge
    -0.06
    caret
    -0.06
    ãģıãģ®
    -0.06
    addin
    -0.06
     Sanchez
    -0.06
    POSITIVE LOGITS
    prime
    0.07
     Chic
    0.06
    sworth
    0.06
    endor
    0.06
     Hardware
    0.06
     pun
    0.06
     hardware
    0.06
    ieten
    0.06
    uya
    0.06
     Chi
    0.06
    Activations Density 0.040%

    No Known Activations