© 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. 17-LLAMASCOPE-RES-131K
    11. 71698
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance or emphasis on a subject

    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
    agas
    -0.07
     Py
    -0.07
    oulos
    -0.07
     verv
    -0.07
     Danger
    -0.07
    ãĥĩãĤ£ãĤ¢
    -0.07
    hod
    -0.06
    ãĤ¤ãĥĦ
    -0.06
    κή
    -0.06
    lli
    -0.06
    POSITIVE LOGITS
     beh
    0.07
     worth
    0.07
    cha
    0.07
    roid
    0.07
    aci
    0.06
    å°¾
    0.06
    arts
    0.06
     ought
    0.06
    erez
    0.06
    Mat
    0.06
    Activations Density 0.027%

    No Known Activations