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. 43652
    Prev
    Next
    INDEX
    Explanations

    phrases related to high prices and financial burdens

    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
     thoughtful
    -0.06
     Fine
    -0.06
     subtle
    -0.06
    ynet
    -0.06
    ntax
    -0.06
    kee
    -0.06
    ắm
    -0.06
     harmless
    -0.06
     delicate
    -0.06
    ainless
    -0.05
    POSITIVE LOGITS
     astronomical
    0.17
     sky
    0.15
     astr
    0.14
     astronom
    0.14
    astr
    0.14
     eye
    0.13
     insane
    0.12
     ex
    0.12
     jaw
    0.12
     garg
    0.12
    Activations Density 0.087%

    No Known Activations