© 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. 83978
    Prev
    Next
    INDEX
    Explanations

    definitions and descriptors

    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
    ses
    -0.07
    dale
    -0.07
    ensively
    -0.06
    aÅŁ
    -0.06
    InView
    -0.06
    IDA
    -0.05
     host
    -0.05
    da
    -0.05
     feeding
    -0.05
     dela
    -0.05
    POSITIVE LOGITS
    ulkan
    0.08
    ungi
    0.08
    aravel
    0.08
     æĻ´
    0.07
    ENTE
    0.07
     Hava
    0.07
    رÙĪج
    0.07
    INGER
    0.07
     Bounty
    0.07
     Yates
    0.07
    Activations Density 0.005%

    No Known Activations