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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40331
    Prev
    Next
    INDEX
    Explanations

    terminology related to academic research and publications

    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
     parcels
    -0.07
     bay
    -0.07
    rov
    -0.06
    Ïħν
    -0.06
    ainty
    -0.06
    bay
    -0.06
     Macros
    -0.06
     parcel
    -0.06
    /assert
    -0.06
    uble
    -0.06
    POSITIVE LOGITS
    ffen
    0.07
    ï¸ı
    0.07
    rowsable
    0.06
    ysa
    0.06
     {!
    0.06
    Æł
    0.06
    æīĢå±ŀ
    0.06
    коз
    0.06
    ven
    0.06
    utsch
    0.06
    Activations Density 0.001%

    No Known Activations