© 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. 58057
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "there" in various grammatical forms

    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
    272
    -0.07
    .nodeType
    -0.07
    /******/
    -0.07
    леÑĢ
    -0.07
     nackte
    -0.07
    аÑĢа
    -0.07
    .sul
    -0.07
    -fit
    -0.07
    rax
    -0.07
    redients
    -0.07
    POSITIVE LOGITS
    utherford
    0.06
     upon
    0.06
     however
    0.06
     Upon
    0.05
     def
    0.05
     Elliott
    0.05
     certain
    0.05
     spec
    0.05
    .spec
    0.05
    oux
    0.05
    Activations Density 0.025%

    No Known Activations