© 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. 129216
    Prev
    Next
    INDEX
    Explanations

    Java import statements and specific coding syntax

    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
    dech
    -0.09
    Ly
    -0.07
    fik
    -0.07
    anzi
    -0.07
    lessly
    -0.07
    æŀĿ
    -0.07
    CAC
    -0.07
    olation
    -0.06
    achs
    -0.06
    522
    -0.06
    POSITIVE LOGITS
    oplast
    0.07
     Batt
    0.06
     Aires
    0.06
    ectar
    0.06
    ô
    0.05
    InProgress
    0.05
    ettel
    0.05
     Luis
    0.05
    üss
    0.05
    etta
    0.05
    Activations Density 0.006%

    No Known Activations