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. 43648
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols used in mathematical or scientific contexts

    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
     I
    -0.06
    ...
    -0.05
     companion
    -0.05
     Companion
    -0.05
     handheld
    -0.05
     driver
    -0.05
    :
    -0.05
     wearable
    -0.05
     compatible
    -0.05
    aille
    -0.05
    POSITIVE LOGITS
     hackers
    0.12
     hacker
    0.10
     attackers
    0.10
     Hacker
    0.10
    Hack
    0.10
     malware
    0.10
     Bitcoins
    0.10
     infect
    0.10
     encrypt
    0.10
     ransom
    0.09
    Activations Density 0.003%

    No Known Activations