© 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. 15-LLAMASCOPE-RES-131K
    11. 104018
    Prev
    Next
    INDEX
    Explanations

    instructions or guidelines related to maintaining or updating systems

    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
     أج
    -0.06
    ackle
    -0.06
    ican
    -0.06
    ie
    -0.06
    è£ħ
    -0.06
    enville
    -0.06
     bio
    -0.06
    延
    -0.06
     Rab
    -0.05
    icans
    -0.05
    POSITIVE LOGITS
    azers
    0.08
    dle
    0.07
    gart
    0.07
    avra
    0.07
    stal
    0.07
    etty
    0.07
    à¥įथल
    0.07
    dish
    0.06
    annt
    0.06
    دار
    0.06
    Activations Density 0.015%

    No Known Activations