© 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. 75717
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
    skirts
    -0.06
    fox
    -0.06
    ion
    -0.06
    etter
    -0.06
    .Expressions
    -0.06
    é£İ
    -0.06
    Bloc
    -0.06
    風
    -0.06
    Sharing
    -0.06
    berman
    -0.05
    POSITIVE LOGITS
    apter
    0.07
     InitializeComponent
    0.07
     NÄĽkterá
    0.07
     miêu
    0.06
    çļĦåľ°
    0.06
    odia
    0.06
    outu
    0.06
     reim
    0.06
     microscopic
    0.06
    rado
    0.06
    Activations Density 0.002%

    No Known Activations