© 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. 128710
    Prev
    Next
    INDEX
    Explanations

    key technical terms and components related to programming and software development

    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
    ↵↵
    -0.07
     ActionTypes
    -0.07
    ayne
    -0.07
    istrovstvÃŃ
    -0.07
    tvrt
    -0.07
    ndef
    -0.07
     Sabb
    -0.07
    MASK
    -0.07
    MBED
    -0.07
    ender
    -0.07
    POSITIVE LOGITS
     inject
    0.06
    ass
    0.06
    æĭ¿
    0.06
    081
    0.06
     WithEvents
    0.06
    ">//
    0.06
    inject
    0.06
    iyan
    0.06
    Ãłnh
    0.06
    dorf
    0.06
    Activations Density 0.007%

    No Known Activations