© 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. 15-LLAMASCOPE-RES-131K
    11. 62530
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating comparisons and notable quantities or characteristics

    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
    ENO
    -0.07
    ault
    -0.07
    eno
    -0.07
    quals
    -0.07
     заклад
    -0.07
    geois
    -0.06
    stakes
    -0.06
    esium
    -0.06
    /includes
    -0.06
    ENC
    -0.06
    POSITIVE LOGITS
    ãģ®ãģ¯
    0.07
     ones
    0.07
    adu
    0.06
    adol
    0.06
    @Web
    0.06
    баÑĩ
    0.06
    atel
    0.06
    urrent
    0.06
     Kear
    0.06
    ë¡ľëĬĶ
    0.06
    Activations Density 0.016%

    No Known Activations