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. 22-LLAMASCOPE-RES-131K
    6. 5769
    Prev
    Next
    INDEX
    Explanations

    terms related to film structure and performance analysis

    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
     Combo
    -0.08
     combo
    -0.07
     QTableWidgetItem
    -0.06
     Pair
    -0.06
     courts
    -0.06
    istr
    -0.06
    rek
    -0.06
     duo
    -0.06
    Pair
    -0.06
    PAIR
    -0.06
    POSITIVE LOGITS
     unity
    0.15
     united
    0.15
     collective
    0.15
     unified
    0.14
     unite
    0.13
     unanim
    0.12
     unify
    0.12
     shared
    0.12
    ãģ¾ãģ¨
    0.12
     pooling
    0.11
    Activations Density 0.009%

    No Known Activations