© 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. 9-LLAMASCOPE-RES-131K
    11. 96526
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or suggestions related to usage and procedures

    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
    arden
    -0.08
    elles
    -0.07
     mainland
    -0.07
    hya
    -0.06
    ersen
    -0.06
    anka
    -0.06
    rics
    -0.06
    vant
    -0.06
    izza
    -0.06
    irs
    -0.06
    POSITIVE LOGITS
    ãģ£ãģ¡
    0.07
    locator
    0.07
    oup
    0.07
    -ÑĤаки
    0.07
    (LogLevel
    0.07
    BarButton
    0.07
    è¨ĵ
    0.06
    ÏĩεδÏĮν
    0.06
    ç¨İ
    0.06
    ëĭĪëĭ¤
    0.06
    Activations Density 0.021%

    No Known Activations