© 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. 15-LLAMASCOPE-RES-131K
    11. 103519
    Prev
    Next
    INDEX
    Explanations

    instances of HTML or PHP opening and closing tags

    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
    abor
    -0.07
    alore
    -0.07
     fle
    -0.06
    éĹ´
    -0.06
    esc
    -0.06
    iac
    -0.06
    MLElement
    -0.06
    ius
    -0.06
    ht
    -0.06
    undi
    -0.06
    POSITIVE LOGITS
     Schro
    0.06
    ackbar
    0.06
    osu
    0.06
    ufig
    0.06
     Legacy
    0.06
     Pere
    0.06
    utzer
    0.06
    isine
    0.06
    landers
    0.06
    egot
    0.06
    Activations Density 0.001%

    No Known Activations