© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83150
    Prev
    Next
    INDEX
    Explanations

    technical terms related to optimization and functionality in various contexts

    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
     è©ķ価
    -0.07
    ughs
    -0.07
    .Toolkit
    -0.07
     UIResponder
    -0.07
    resar
    -0.06
    .asInstanceOf
    -0.06
    ÑĨен
    -0.06
    ör
    -0.06
    etri
    -0.06
    çĶľ
    -0.06
    POSITIVE LOGITS
     ensures
    0.09
     ensure
    0.09
     allows
    0.08
     helps
    0.08
     further
    0.08
     make
    0.08
     allow
    0.07
     provides
    0.07
     help
    0.07
     позволÑıеÑĤ
    0.07
    Activations Density 0.030%

    No Known Activations