© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 88716
    Prev
    Next
    INDEX
    Explanations

    phrases that evaluate storytelling quality and transformation potential

    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
    ensa
    -0.08
    icha
    -0.07
    ensing
    -0.06
    ego
    -0.06
    à¹Īว
    -0.06
     sovere
    -0.06
    rouw
    -0.06
    utting
    -0.06
    herits
    -0.06
    à¹Ģà¸ļ
    -0.06
    POSITIVE LOGITS
     can
    0.09
     even
    0.08
     sometimes
    0.08
    even
    0.08
    Sometimes
    0.07
    ç«Ł
    0.07
     indeed
    0.07
    åİŁæĿ¥
    0.07
    )((((
    0.07
    sometimes
    0.07
    Activations Density 0.046%

    No Known Activations