Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 40403
    Prev
    Next
    INDEX
    Explanations

    instances of semicolons in the text

    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
    λά
    -0.07
    lessly
    -0.07
    <<<
    -0.06
     dara
    -0.06
    ptr
    -0.06
    æķ¬
    -0.06
    eller
    -0.06
    iros
    -0.06
    å¹³
    -0.06
    ager
    -0.06
    POSITIVE LOGITS
    ERRU
    0.07
    дÑĸл
    0.07
    URLException
    0.07
    iscrim
    0.07
     class
    0.07
    /Area
    0.06
    chandle
    0.06
    .AnchorStyles
    0.06
    ofday
    0.06
    holm
    0.06
    Activations Density 0.012%

    No Known Activations