© 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. 88310
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to functions and variables in a formal context

    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
    c
    -0.07
    ;amp
    -0.06
    anova
    -0.06
    tur
    -0.06
    tout
    -0.06
    ivalent
    -0.06
     pai
    -0.06
    æľ
    -0.06
    ileo
    -0.06
    å±
    -0.06
    POSITIVE LOGITS
    ubber
    0.07
    hoff
    0.06
    zag
    0.06
    sted
    0.06
    698
    0.06
    -strip
    0.06
    ойно
    0.06
    oidal
    0.06
    usercontent
    0.06
    ¢
    0.06
    Activations Density 0.763%

    No Known Activations