© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 58533
    Prev
    Next
    INDEX
    Explanations

    punctuation and conversational markers 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
     Dude
    -0.07
    anke
    -0.07
    ÙĬÙĩ
    -0.07
    ylko
    -0.06
    кÑģп
    -0.06
    ĭ
    -0.06
     Ingram
    -0.06
     è¾
    -0.06
    etting
    -0.06
     Yup
    -0.06
    POSITIVE LOGITS
    aphore
    0.06
     anyway
    0.06
     therefore
    0.06
    empo
    0.06
    tual
    0.06
    kla
    0.06
    iversit
    0.06
     version
    0.06
    .force
    0.06
    ListBox
    0.06
    Activations Density 0.033%

    No Known Activations