© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3752
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking solutions and addressing concerns

    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
    ebo
    -0.08
    ÅĻet
    -0.07
    artner
    -0.07
    kup
    -0.07
    stdarg
    -0.07
    mons
    -0.07
     dere
    -0.07
    brero
    -0.07
     tablesp
    -0.07
    ÅĻik
    -0.07
    POSITIVE LOGITS
     rocky
    0.06
     department
    0.06
     cứng
    0.06
    icorn
    0.06
     quotid
    0.05
    íĮħ
    0.05
     his
    0.05
    ision
    0.05
    ataire
    0.05
    issions
    0.05
    Activations Density 0.001%

    No Known Activations