© 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. 77818
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and other structural elements in the text

    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
    è¾ħ
    -0.06
     hod
    -0.06
    otten
    -0.06
    ÑĢоÑĪ
    -0.06
     Moy
    -0.06
     Deg
    -0.06
    arket
    -0.06
    Ïį
    -0.06
    ź
    -0.06
    åįļ
    -0.06
    POSITIVE LOGITS
    atra
    0.07
    arem
    0.07
    oa
    0.07
    åĩĨ
    0.06
    .Xr
    0.06
     táºŃp
    0.06
    {{{
    0.06
    ja
    0.06
     DOI
    0.06
    SharedPointer
    0.06
    Activations Density 0.000%

    No Known Activations