© 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. 39752
    Prev
    Next
    INDEX
    Explanations

    specific accented characters or letters in 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
    anded
    -0.07
    avr
    -0.07
    loquent
    -0.07
     ì½
    -0.07
    iris
    -0.06
    vals
    -0.06
    temps
    -0.06
    AMPLE
    -0.06
    ivals
    -0.06
     Dollar
    -0.06
    POSITIVE LOGITS
     tô
    0.07
    ska
    0.07
    uttle
    0.07
    á»ijt
    0.06
    .Persistent
    0.06
    رد
    0.06
    aub
    0.06
    Ùĩ
    0.06
    ANDARD
    0.06
     unten
    0.06
    Activations Density 0.005%

    No Known Activations