© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106193
    Prev
    Next
    INDEX
    Explanations

    XML or HTML tags and configurations

    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
    ç½²
    -0.07
     Fine
    -0.07
    aina
    -0.06
    enek
    -0.06
    afs
    -0.06
    ÑĪев
    -0.06
    podob
    -0.06
    obot
    -0.06
    eneg
    -0.06
    MLS
    -0.06
    POSITIVE LOGITS
     item
    0.07
    endoza
    0.06
    284
    0.06
     LRV
    0.06
    036
    0.06
    {Name
    0.06
    ircular
    0.06
    attern
    0.06
    ÅĪ
    0.06
    ä¹ĭä¸Ģ
    0.06
    Activations Density 0.013%

    No Known Activations