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. 43587
    Prev
    Next
    INDEX
    Explanations

    mentions of digital rights and related initiatives

    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
     Sew
    -0.06
    raman
    -0.06
    ozy
    -0.06
    NST
    -0.06
     Trout
    -0.06
    eton
    -0.05
    RSS
    -0.05
    oux
    -0.05
     (::
    -0.05
     Idaho
    -0.05
    POSITIVE LOGITS
     Labels
    0.10
     Copyright
    0.10
     ICMP
    0.10
     labels
    0.10
     trade
    0.10
    PRS
    0.09
     CIS
    0.09
    IMP
    0.09
    Copyright
    0.09
     Publishing
    0.09
    Activations Density 0.011%

    No Known Activations