© 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. 82589
    Prev
    Next
    INDEX
    Explanations

    references to specific statistical values or terms

    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
    ÃĹ↵↵
    -0.08
    ej
    -0.07
    egral
    -0.07
    inson
    -0.07
    عÙĦÙĪÙħات
    -0.07
    éĥİ
    -0.07
    :href
    -0.07
    osate
    -0.07
    ahren
    -0.07
    ablish
    -0.07
    POSITIVE LOGITS
    istical
    0.11
    utory
    0.10
    ellite
    0.09
    istically
    0.09
     quo
    0.07
    vation
    0.07
    emachine
    0.06
    653
    0.06
    craft
    0.06
     Jude
    0.06
    Activations Density 0.007%

    No Known Activations