© 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. 78143
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and formal properties within a technical 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
    inton
    -0.06
    Ŀ
    -0.06
     cust
    -0.06
     Mist
    -0.06
    idth
    -0.05
     respect
    -0.05
    alta
    -0.05
    ãģ®åŃIJ
    -0.05
    ameleon
    -0.05
    alt
    -0.05
    POSITIVE LOGITS
    ndef
    0.09
    ħn
    0.08
     definition
    0.08
    Definition
    0.08
     Definition
    0.08
    å®ļä¹ī
    0.07
    definitions
    0.07
    sworth
    0.07
    asser
    0.07
     DEFIN
    0.07
    Activations Density 0.178%

    No Known Activations