© 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. 105957
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and technical specifications

    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
    ylland
    -0.08
     poil
    -0.08
    ìĿ´íĦ°
    -0.08
    alus
    -0.08
    jeme
    -0.07
    ìĿ´íĬ¸
    -0.07
    emey
    -0.07
     explan
    -0.07
    reu
    -0.07
    burgh
    -0.07
    POSITIVE LOGITS
    ware
    0.06
     Wenger
    0.06
    311
    0.05
    jsx
    0.05
    ities
    0.05
    ç½
    0.05
    orption
    0.05
    hips
    0.05
    hip
    0.05
     le
    0.05
    Activations Density 0.125%

    No Known Activations