Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5327
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences or questions

    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
    iero
    -0.07
     liá»ĩu
    -0.07
     ActionTypes
    -0.06
    opher
    -0.06
    illi
    -0.06
    ubat
    -0.06
    innitus
    -0.06
     Nin
    -0.06
     Stam
    -0.06
    eced
    -0.06
    POSITIVE LOGITS
    compan
    0.07
     ninh
    0.07
    vatel
    0.06
    illisecond
    0.06
    addtogroup
    0.06
    ,readonly
    0.06
    iez
    0.06
    ogan
    0.06
    çİĦ
    0.06
    enor
    0.06
    Activations Density 0.000%

    No Known Activations