Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5387
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and 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
    ugal
    -0.07
    ivol
    -0.07
    astics
    -0.07
    hana
    -0.06
    çĭIJ
    -0.06
    åΰåºķ
    -0.06
    riers
    -0.06
     миÑĤ
    -0.06
     sockfd
    -0.06
    ibaba
    -0.06
    POSITIVE LOGITS
     Perl
    0.11
     Mal
    0.09
     Pen
    0.07
    Mal
    0.07
     Joh
    0.07
     Malaysia
    0.07
     infect
    0.07
     Malcolm
    0.07
     Malaysian
    0.07
     Kuala
    0.06
    Activations Density 0.008%

    No Known Activations