© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127014
    Prev
    Next
    INDEX
    Explanations

    announcements related to contests and prize distributions

    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
    ellas
    -0.08
    ionario
    -0.07
    олоÑģ
    -0.07
     âĹĦ
    -0.07
    abay
    -0.07
     Kaynak
    -0.07
    лим
    -0.07
    alent
    -0.07
    criptors
    -0.07
    izons
    -0.07
    POSITIVE LOGITS
     winners
    0.06
     Ler
    0.06
    aml
    0.05
     deter
    0.05
     winner
    0.05
     Haut
    0.05
     announced
    0.05
     internally
    0.05
     who
    0.05
     GMT
    0.05
    Activations Density 0.003%

    No Known Activations