© 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. 15-LLAMASCOPE-RES-131K
    11. 89914
    Prev
    Next
    INDEX
    Explanations

    complex arguments surrounding social and political dynamics

    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
    ctrine
    -0.08
    ERRU
    -0.07
    vig
    -0.07
    riad
    -0.07
    ego
    -0.07
    ceipt
    -0.07
    altet
    -0.07
    ýval
    -0.06
    yor
    -0.06
    cest
    -0.06
    POSITIVE LOGITS
     allegedly
    0.07
     necessarily
    0.06
     merely
    0.06
     supposedly
    0.06
    Hashtable
    0.06
     alleged
    0.06
    åįĺ
    0.06
     either
    0.06
     simply
    0.06
     contin
    0.06
    Activations Density 0.032%

    No Known Activations