© 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. 17-LLAMASCOPE-RES-131K
    6. 3159
    Prev
    Next
    INDEX
    Explanations

    references to consumer protection and business ratings

    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
    wand
    -0.07
    _sy
    -0.07
    EMU
    -0.06
    sponsor
    -0.06
    SCALE
    -0.06
     Ñģел
    -0.06
    é»İ
    -0.06
    reno
    -0.06
    .timestamps
    -0.06
    ht
    -0.06
    POSITIVE LOGITS
     BBB
    0.08
     Yelp
    0.08
     consumer
    0.08
     Consumer
    0.07
     rating
    0.07
     ratings
    0.07
     consumers
    0.07
    Consumer
    0.07
    raud
    0.07
    consumer
    0.07
    Activations Density 0.003%

    No Known Activations