© 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. 28944
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to computer systems and programming

    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
    ocos
    -0.07
     editorial
    -0.06
    idon
    -0.06
     Editorial
    -0.06
    .setDefault
    -0.06
    اÙħÙĦ
    -0.06
     tackled
    -0.06
     deposition
    -0.06
    pace
    -0.06
    Semaphore
    -0.06
    POSITIVE LOGITS
     glGet
    0.08
     obtain
    0.08
     obtaining
    0.08
    èİ·åıĸ
    0.08
     obtains
    0.07
     Obtain
    0.07
    åıĸå¾Ĺ
    0.07
     lấy
    0.07
     get
    0.07
     info
    0.07
    Activations Density 0.067%

    No Known Activations