© 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. 126999
    Prev
    Next
    INDEX
    Explanations

    terms related to emotional or psychological states and conflicts

    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
    егоÑĢ
    -0.07
    ValuePair
    -0.07
    .EventHandler
    -0.06
    andles
    -0.06
    ederland
    -0.06
    ligt
    -0.06
     Dit
    -0.06
    ertoire
    -0.06
    306
    -0.06
    etine
    -0.06
    POSITIVE LOGITS
     happens
    0.09
     happened
    0.08
     happen
    0.08
     erfol
    0.07
     date
    0.07
    aldo
    0.07
    Occurred
    0.07
     happening
    0.07
    aidu
    0.07
    eness
    0.07
    Activations Density 0.057%

    No Known Activations