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. 43950
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and personal experiences

    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
    zman
    -0.07
    iphy
    -0.06
    oser
    -0.06
    aub
    -0.06
    igor
    -0.06
    ophy
    -0.06
    ì¹Ļ
    -0.06
    zew
    -0.06
     voksne
    -0.06
    _dl
    -0.06
    POSITIVE LOGITS
     live
    0.10
     wondering
    0.10
     urgently
    0.09
     recently
    0.08
     reside
    0.08
     desperately
    0.08
     just
    0.08
     apology
    0.07
     lives
    0.07
     work
    0.07
    Activations Density 0.043%

    No Known Activations