© 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. 27361
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about qualities and characteristics of people or things

    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
    firm
    -0.06
    us
    -0.06
    SEN
    -0.06
     Ipsum
    -0.06
     çĶ°
    -0.06
    pr
    -0.06
    ol
    -0.06
    i
    -0.06
    ibre
    -0.06
     alike
    -0.06
    POSITIVE LOGITS
    icket
    0.07
    uida
    0.07
    .gwt
    0.07
    ÐĺТ
    0.07
    igkeit
    0.07
    бÑĥдÑĮ
    0.07
     gsi
    0.07
    uga
    0.07
    illisecond
    0.07
    ваннÑı
    0.06
    Activations Density 0.056%

    No Known Activations