© 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. 62317
    Prev
    Next
    INDEX
    Explanations

    phrases related to sending and receiving messages or communications

    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
    eka
    -0.06
     lanc
    -0.06
    rades
    -0.05
    abh
    -0.05
    alam
    -0.05
    erman
    -0.05
    peer
    -0.05
    ีว
    -0.05
     rpm
    -0.05
    ัย
    -0.05
    POSITIVE LOGITS
    ToDevice
    0.09
    ارة
    0.08
    ibel
    0.07
    Å¡ov
    0.07
    HAL
    0.07
    ká
    0.07
    endir
    0.07
    į¨
    0.07
     Blanch
    0.07
    èī¦
    0.07
    Activations Density 0.017%

    No Known Activations