© 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. 105602
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
    оба
    -0.07
    ấp
    -0.07
    iest
    -0.07
    воÑİ
    -0.07
    .VisualBasic
    -0.07
     ThemeData
    -0.07
    ÄĽst
    -0.07
    ãģĵãĤĵ
    -0.07
    rown
    -0.07
     GUIContent
    -0.07
    POSITIVE LOGITS
    indsight
    0.08
    @nate
    0.06
    eton
    0.06
     silhouette
    0.06
    oger
    0.06
     cla
    0.05
     COMMENTS
    0.05
    sic
    0.05
    -unstyled
    0.05
    iol
    0.05
    Activations Density 0.040%

    No Known Activations