© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16942
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to computer science and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Programming language elements, technical identifiers, and domain-specific terms that serve as functional elements within structured text like code, academic papers, and configuration files.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    $MESS
    -0.11
    'gc
    -0.10
    .scalablytyped
    -0.09
     ÑĤабли
    -0.08
    пÑĢиклад
    -0.08
    $LANG
    -0.08
    ¶ģ
    -0.08
    //{{
    -0.08
    Ø´ÙħارÛĮ
    -0.08
    Uvs
    -0.07
    POSITIVE LOGITS
     latter
    0.08
    Âł
    0.07
    icense
    0.05
    malink
    0.05
    
    0.05
    thing
    0.05
     ...↵
    0.05
    ht
    0.05
    adder
    0.05
    uding
    0.05
    Activations Density 0.503%

    No Known Activations