© 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 EvalsExportsinterp-engineNEWAPI 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. 107548
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance and values of outcomes or results

    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
    erty
    -0.08
    edad
    -0.07
     klim
    -0.07
     genie
    -0.06
    eneric
    -0.06
    337
    -0.06
    cus
    -0.06
     bids
    -0.06
    bart
    -0.06
    pf
    -0.06
    POSITIVE LOGITS
     mattered
    0.11
     ultimately
    0.09
     matters
    0.09
     Matters
    0.09
     important
    0.09
    important
    0.09
     thôi
    0.09
     Ultimately
    0.08
    éĩįè¦ģ
    0.08
     Important
    0.08
    Activations Density 0.028%

    No Known Activations