© 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. 106262
    Prev
    Next
    INDEX
    Explanations

    technical terminology and code related to audio processing

    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
    ulate
    -0.07
    ovich
    -0.06
     Hoe
    -0.06
     metab
    -0.06
    ssel
    -0.06
    å°ijå¹´
    -0.06
     coef
    -0.06
    urgeon
    -0.06
     rel
    -0.06
    ij
    -0.06
    POSITIVE LOGITS
     Watson
    0.07
     training
    0.07
     train
    0.07
     pai
    0.07
    commons
    0.07
    -training
    0.07
    /grpc
    0.07
    æ£Ģ
    0.07
    ffd
    0.06
     speech
    0.06
    Activations Density 0.012%

    No Known Activations