© 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. 9-LLAMASCOPE-RES-131K
    11. 96300
    Prev
    Next
    INDEX
    Explanations

    references to audio and video formats

    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
     coll
    -0.07
    agnost
    -0.06
     alm
    -0.06
     Digital
    -0.06
    ết
    -0.06
     suff
    -0.05
    OST
    -0.05
     mer
    -0.05
    æ¡Ī
    -0.05
    廳
    -0.05
    POSITIVE LOGITS
    ائÙĦ
    0.07
    vit
    0.07
    ergic
    0.07
    άνι
    0.07
     ActionController
    0.07
    AEA
    0.07
    è¾°
    0.07
    answered
    0.07
    (div
    0.07
    çİ
    0.07
    Activations Density 0.002%

    No Known Activations