© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 79128
    Prev
    Next
    INDEX
    Explanations

    references to file transfer and email protocols

    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
    UNET
    -0.07
    alous
    -0.07
    igate
    -0.06
    á»įt
    -0.06
    hq
    -0.06
    erial
    -0.06
    ums
    -0.06
    æĬ¼
    -0.06
    owl
    -0.06
     Detector
    -0.06
    POSITIVE LOGITS
    ://
    0.09
    sport
    0.08
    going
    0.07
    sen
    0.07
    sse
    0.07
    ãĤ¢ãĥĭãĥ¡
    0.07
    sak
    0.06
    ÑĩиÑģ
    0.06
    :\/\/
    0.06
    sj
    0.06
    Activations Density 0.010%

    No Known Activations