© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3202
    Prev
    Next
    INDEX
    Explanations

    references to Nintendo 3DS and related gaming experiences

    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
     tel
    -0.06
    ë¹Ļ
    -0.06
    ayout
    -0.06
     Audi
    -0.06
     mand
    -0.05
     Kub
    -0.05
     Rack
    -0.05
    braco
    -0.05
     Peters
    -0.05
    å¾Ħ
    -0.05
    POSITIVE LOGITS
    quirer
    0.07
    ovky
    0.07
    æĬĺ
    0.07
    arus
    0.07
    zá
    0.07
    egra
    0.07
    mmc
    0.07
    _MC
    0.07
    ìĥµ
    0.07
    jist
    0.07
    Activations Density 0.002%

    No Known Activations