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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 43596
    Prev
    Next
    INDEX
    Explanations

    key programming concepts and data structures

    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
    orch
    -0.08
    lectron
    -0.08
    imit
    -0.08
    outil
    -0.08
    imagin
    -0.08
    IGIN
    -0.07
     EDUC
    -0.07
    infer
    -0.07
    educ
    -0.07
    inject
    -0.07
    POSITIVE LOGITS
     Esp
    0.07
     Ent
    0.06
     ãĤ¨
    0.06
     Exp
    0.06
    berry
    0.06
     Eng
    0.06
     Williamson
    0.06
     battery
    0.06
    relationship
    0.06
     Ext
    0.06
    Activations Density 0.030%

    No Known Activations