© 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 EvalsExportsinterp-engineNEWAPI 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. 73819
    Prev
    Next
    INDEX
    Explanations

    elements related to product evaluations and consumer 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
     mastur
    -0.07
    cheid
    -0.07
     saturn
    -0.07
    Then
    -0.06
    inges
    -0.06
     THEN
    -0.06
     then
    -0.06
     же
    -0.06
    slu
    -0.06
     Then
    -0.06
    POSITIVE LOGITS
    ÙĨج
    0.07
    xis
    0.07
    licer
    0.07
    935
    0.06
    188
    0.06
    ãĥ©ãĤ¹
    0.06
    944
    0.06
    cco
    0.06
     def
    0.06
    jam
    0.06
    Activations Density 0.049%

    No Known Activations