Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16471
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their achievements

    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
    òng
    -0.08
    %X
    -0.07
    loquent
    -0.07
    inue
    -0.07
    obby
    -0.07
    ENOMEM
    -0.06
    #af
    -0.06
    abee
    -0.06
    DEX
    -0.06
    ember
    -0.06
    POSITIVE LOGITS
     modern
    0.11
    Modern
    0.09
    modern
    0.09
     Modern
    0.09
    çݰ代
    0.08
     moderne
    0.08
     contemporary
    0.08
     generation
    0.08
     moden
    0.08
     modem
    0.07
    Activations Density 0.020%

    No Known Activations