© 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. 74648
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "It" or "They" that describe various states or properties

    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
    itsu
    -0.08
    arel
    -0.08
    åĨµ
    -0.07
    renc
    -0.07
    itz
    -0.07
    à¸į
    -0.07
    ÄĽst
    -0.07
    éĿ¢ç§¯
    -0.07
    poÄįet
    -0.07
    ewe
    -0.06
    POSITIVE LOGITS
    tica
    0.06
     should
    0.06
    uish
    0.06
    anger
    0.06
     easiest
    0.06
    bic
    0.06
     will
    0.06
    676
    0.05
    Spacer
    0.05
    uro
    0.05
    Activations Density 0.028%

    No Known Activations