© 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. 106466
    Prev
    Next
    INDEX
    Explanations

    references to financial performance metrics and benchmarks

    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
     breweries
    -0.07
     brewery
    -0.07
    aney
    -0.06
    Forgery
    -0.06
     SUBSTITUTE
    -0.06
    úc
    -0.06
    UsageId
    -0.06
    agan
    -0.06
     advanced
    -0.06
    ặt
    -0.06
    POSITIVE LOGITS
     subscription
    0.08
     Subscription
    0.07
    Clients
    0.07
     subscriptions
    0.07
    òng
    0.07
    Subscription
    0.07
     bunk
    0.07
     clients
    0.06
    ĶåĽŀ
    0.06
    enn
    0.06
    Activations Density 0.004%

    No Known Activations