© 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. 15-LLAMASCOPE-RES-131K
    6. 1566
    Prev
    Next
    INDEX
    Explanations

    references to feminist texts and discussions on social issues

    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
     temporary
    -0.07
     /
    -0.06
     rival
    -0.06
     simple
    -0.06
     Temporary
    -0.06
     &
    -0.06
     
    -0.06
     temporarily
    -0.06
    ään
    -0.06
    ocio
    -0.06
    POSITIVE LOGITS
    å¬
    0.08
    олож
    0.08
    ìĶĢ
    0.08
    .Serial
    0.08
     caffe
    0.07
    ?↵↵↵↵
    0.07
     بØŃØ«
    0.07
     ninete
    0.07
    åĢį
    0.07
    =pk
    0.07
    Activations Density 0.005%

    No Known Activations