© 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. 106845
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to diagnostics and methodologies

    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
    abo
    -0.06
    apper
    -0.06
    APPER
    -0.06
    ptron
    -0.06
    iman
    -0.06
    agua
    -0.06
    aren
    -0.06
    agu
    -0.06
    allen
    -0.05
    .Direction
    -0.05
    POSITIVE LOGITS
     enable
    0.15
     enables
    0.15
     allows
    0.14
     allow
    0.14
     enabling
    0.14
     ermög
    0.13
     allowing
    0.13
    allow
    0.13
    allows
    0.13
     позволÑıеÑĤ
    0.13
    Activations Density 0.091%

    No Known Activations