© 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. 118914
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis or significance in a context

    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
     sum
    -0.06
    .Îł
    -0.06
    evin
    -0.06
    aze
    -0.06
     Garrett
    -0.06
    kn
    -0.06
    anela
    -0.06
    ivor
    -0.06
    uk
    -0.06
    asma
    -0.05
    POSITIVE LOGITS
     especialmente
    0.08
     applies
    0.08
     especially
    0.08
     true
    0.08
    788
    0.08
     verdade
    0.07
    true
    0.07
    urer
    0.07
    orsch
    0.07
     ειδ
    0.07
    Activations Density 0.008%

    No Known Activations