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

    Neuronpedia

    Jacobian LensNEW
    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. 88466
    Prev
    Next
    INDEX
    Explanations

    references to professional credentials and experiences

    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
    rescia
    -0.09
    bane
    -0.08
    tual
    -0.07
    Ø´ÙĨ
    -0.07
    #__
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
    urat
    -0.07
    cki
    -0.07
    alim
    -0.07
    baru
    -0.07
    POSITIVE LOGITS
     hometown
    0.07
     briefly
    0.06
     trace
    0.06
    .cloudflare
    0.06
    swire
    0.06
     postings
    0.06
    879
    0.05
     lit
    0.05
     Rankings
    0.05
    åĸ¶
    0.05
    Activations Density 0.025%

    No Known Activations