© 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. 61597
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and question marks

    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
    pei
    -0.08
    ertino
    -0.07
    $rs
    -0.06
    âĢ»
    -0.06
    hle
    -0.06
    isOk
    -0.06
     Tang
    -0.06
    ahr
    -0.06
    icrosoft
    -0.06
    _INCLUDED
    -0.06
    POSITIVE LOGITS
    надлеж
    0.08
     Modi
    0.07
    alian
    0.06
    ajan
    0.06
    @js
    0.06
    .LA
    0.06
    .esp
    0.06
    owa
    0.06
    placeholders
    0.06
    olian
    0.06
    Activations Density 0.068%

    No Known Activations