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. 44218
    Prev
    Next
    INDEX
    Explanations

    titles or roles related to management and leadership positions

    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
    .scalablytyped
    -0.08
    resultCode
    -0.07
    edin
    -0.06
    ÏĩÏĮ
    -0.06
    èª
    -0.06
    bei
    -0.06
     Magnus
    -0.06
    oms
    -0.06
    _resolver
    -0.06
    aid
    -0.06
    POSITIVE LOGITS
     member
    0.13
     Member
    0.12
     principal
    0.12
     Principal
    0.11
     partner
    0.10
     Partner
    0.10
    Member
    0.10
     Princip
    0.10
     members
    0.10
    member
    0.09
    Activations Density 0.006%

    No Known Activations