© 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. 130225
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting roles or contexts of actions and subjects

    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
    iland
    -0.08
     fate
    -0.06
    reich
    -0.06
    MainThread
    -0.06
    bao
    -0.06
    avaÅŁ
    -0.06
     reasons
    -0.06
    bast
    -0.05
     cru
    -0.05
    oubted
    -0.05
    POSITIVE LOGITS
    _Generic
    0.07
    æĽ¿
    0.07
     wor
    0.07
    altern
    0.07
    alles
    0.07
    ald
    0.07
     à¤ĸड
    0.07
    ìľĦìĽIJ
    0.06
    .Singleton
    0.06
     ìĹĨìĹĪ
    0.06
    Activations Density 0.012%

    No Known Activations