© 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. 851
    Prev
    Next
    INDEX
    Explanations

    copyright and intellectual property related elements

    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
    (
    -0.06
     (
    -0.06
    ÂŃ
    -0.06
    ↵
    -0.06
    ;
    -0.06
    rops
    -0.06
    ,
    -0.06
    .
    -0.06
     Dise
    -0.06
    cbc
    -0.06
    POSITIVE LOGITS
    	Copyright
    0.09
    chwitz
    0.09
    å®Ļ
    0.08
    opyright
    0.08
    erdem
    0.08
    taj
    0.08
    tü
    0.08
    먹
    0.08
    ãĤ¤ãĥī
    0.08
    ÑĪиб
    0.08
    Activations Density 0.006%

    No Known Activations