© 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. 16569
    Prev
    Next
    INDEX
    Explanations

    function declarations in code

    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
    lie
    -0.07
    estre
    -0.06
    arem
    -0.06
    iffin
    -0.06
    à¹Ģว
    -0.06
    awk
    -0.06
    kee
    -0.06
    peat
    -0.06
    è¶³
    -0.06
     cui
    -0.06
    POSITIVE LOGITS
     Aires
    0.07
     inf
    0.07
    ORY
    0.06
    ãĥ¡ãĥ³ãĥĪ
    0.06
    lero
    0.06
    HN
    0.06
    (/*
    0.06
    omik
    0.06
    WithValue
    0.06
    «
    0.06
    Activations Density 0.002%

    No Known Activations