© 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. 4819
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that indicate addition or continuation of ideas

    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
    âĢ¦↵
    -0.08
    -
    -0.07
     âĢ¦↵
    -0.06
    <
    -0.06
    ...↵
    -0.06
    reira
    -0.06
    -h
    -0.06
    ÂŃ
    -0.06
     physiological
    -0.06
     and
    -0.06
    POSITIVE LOGITS
    Interop
    0.09
    Æ¡
    0.08
    еко
    0.08
    ÙĬدا
    0.08
    ụn
    0.08
    obec
    0.08
    à¤Ĭ
    0.08
     yukarı
    0.08
    ì§ĢëıĦ
    0.08
    åĨµ
    0.08
    Activations Density 0.063%

    No Known Activations