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. 43669
    Prev
    Next
    INDEX
    Explanations

    descriptors of personality traits and character dynamics

    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
    ä¹±
    -0.07
    theid
    -0.07
    abal
    -0.07
    ÙĪØº
    -0.07
    Ø´ÙħاÙĦÛĮ
    -0.06
     aktu
    -0.06
     Sexo
    -0.06
    olley
    -0.06
    ruba
    -0.06
    adero
    -0.06
    POSITIVE LOGITS
     reserved
    0.16
     quiet
    0.14
     subdued
    0.13
     underst
    0.13
     Reserved
    0.13
     shy
    0.13
     modest
    0.13
     restrained
    0.13
     quieter
    0.12
     humble
    0.12
    Activations Density 0.083%

    No Known Activations