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. 43722
    Prev
    Next
    INDEX
    Explanations

    references to political parties or entities

    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
     Kohana
    -0.08
    é³
    -0.07
    IntArray
    -0.07
    npos
    -0.07
    Congress
    -0.07
    ç¿°
    -0.07
    RouterModule
    -0.07
     Kapoor
    -0.06
    ilo
    -0.06
    enko
    -0.06
    POSITIVE LOGITS
     Fri
    0.16
     Abr
    0.15
     Em
    0.15
     Lig
    0.15
     Ap
    0.14
    Fri
    0.13
     Lomb
    0.13
     Trent
    0.13
     Ven
    0.12
     March
    0.12
    Activations Density 0.026%

    No Known Activations