© 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. 119572
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize relationships or connections

    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
    pare
    -0.06
     Igor
    -0.06
     
    -0.06
    orz
    -0.06
     respectively
    -0.06
     concerned
    -0.06
    ucci
    -0.06
    cent
    -0.06
     dare
    -0.06
     <>
    -0.05
    POSITIVE LOGITS
     grap
    0.07
    거리
    0.07
     soudu
    0.07
    ograph
    0.07
    andom
    0.07
    phin
    0.07
    ñ
    0.06
    abe
    0.06
    /Area
    0.06
     rád
    0.06
    Activations Density 0.030%

    No Known Activations