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. 22-LLAMASCOPE-RES-131K
    6. 5506
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant factors or consequences in workplace 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
    èϽçĦ¶
    -0.08
    Äįel
    -0.08
    ouz
    -0.07
     Göz
    -0.07
    ãģ§ãģĻãģŃ
    -0.07
    illez
    -0.07
    .heroku
    -0.07
    æĪª
    -0.07
     although
    -0.07
    -dropdown
    -0.07
    POSITIVE LOGITS
     here
    0.11
     Here
    0.09
    Here
    0.09
     so
    0.08
    .Here
    0.08
     why
    0.08
     maybe
    0.08
    here
    0.07
     experts
    0.07
    _here
    0.07
    Activations Density 0.027%

    No Known Activations