© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 3663
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate success or achievement

    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
    ä½ł
    -0.07
    ahoma
    -0.07
     you
    -0.06
    ä½łçļĦ
    -0.06
     basically
    -0.06
     ours
    -0.06
    ouri
    -0.06
     we
    -0.06
    æĪij们çļĦ
    -0.06
     aber
    -0.06
    POSITIVE LOGITS
     tod
    0.09
    Additionally
    0.08
     Additionally
    0.08
     Already
    0.08
    Already
    0.08
     additional
    0.07
    .www
    0.07
     last
    0.07
    .@
    0.07
     recent
    0.07
    Activations Density 0.025%

    No Known Activations