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. 5407
    Prev
    Next
    INDEX
    Explanations

    concepts related to subjective evaluation and personal opinions

    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
    braco
    -0.08
    egral
    -0.08
    partment
    -0.07
    bourg
    -0.07
    ework
    -0.07
     EntityState
    -0.07
    ument
    -0.06
    лиÑĪ
    -0.06
    ÙĪØ²
    -0.06
    roit
    -0.06
    POSITIVE LOGITS
     subjective
    0.21
     personal
    0.17
     individual
    0.14
     opinion
    0.14
    personal
    0.13
    åĢĭ人
    0.13
    个人
    0.12
     Personal
    0.12
    Personal
    0.12
     opinions
    0.12
    Activations Density 0.066%

    No Known Activations