© 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. 28902
    Prev
    Next
    INDEX
    Explanations

    statements and claims made by individuals or organizations

    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
    ÑĩÑĥк
    -0.08
     же
    -0.08
     pÅĻitom
    -0.07
    νη
    -0.07
    uitka
    -0.07
    ICAST
    -0.06
    Äįan
    -0.06
    èŀį
    -0.06
     à¤ĩसल
    -0.06
    meld
    -0.06
    POSITIVE LOGITS
    763
    0.07
    ally
    0.06
    å°±ä¼ļ
    0.06
    rim
    0.06
    423
    0.06
    rome
    0.06
    476
    0.05
    ellen
    0.05
     Bye
    0.05
     advisory
    0.05
    Activations Density 0.039%

    No Known Activations