© 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. 94018
    Prev
    Next
    INDEX
    Explanations

    phrases indicating rankings or evaluations

    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
    rray
    -0.08
    elves
    -0.07
    lico
    -0.07
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.07
    .Automation
    -0.07
    anan
    -0.07
    碼
    -0.06
    ãĥŁãĥ¥
    -0.06
    /apt
    -0.06
    umo
    -0.06
    POSITIVE LOGITS
    /high
    0.07
    /generated
    0.06
    ever
    0.06
     amongst
    0.06
     among
    0.06
    805
    0.06
    overall
    0.06
    оÑĤÑĮ
    0.06
     overall
    0.06
    .strategy
    0.06
    Activations Density 0.005%

    No Known Activations