© 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. 9-LLAMASCOPE-RES-131K
    6. 95000
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases that indicate comparisons or contrasts

    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
    ocha
    -0.08
    anka
    -0.07
    ugar
    -0.07
    chg
    -0.07
    ozor
    -0.07
    uhn
    -0.07
    isha
    -0.07
    charg
    -0.07
    ázi
    -0.07
    kowski
    -0.07
    POSITIVE LOGITS
     others
    0.07
     pl
    0.07
    arios
    0.07
     com
    0.06
     other
    0.06
     elsewhere
    0.06
     uniform
    0.06
     otherwise
    0.06
    Ñĸд
    0.05
    gress
    0.05
    Activations Density 0.059%

    No Known Activations