© 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. 126080
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or breaks in sentence flow

    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
    mares
    -0.07
    orld
    -0.07
    bes
    -0.06
    ptide
    -0.06
    ement
    -0.06
     Alman
    -0.06
    udos
    -0.06
    stry
    -0.06
    straint
    -0.06
    lom
    -0.06
    POSITIVE LOGITS
     shm
    0.09
    alink
    0.08
     INTERRU
    0.07
    amon
    0.07
    addin
    0.07
     Taxes
    0.07
    ENCH
    0.07
    IFS
    0.07
     Interrupt
    0.07
    ë°ĺ기
    0.07
    Activations Density 0.066%

    No Known Activations