© 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. 93748
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exceptional quality or uniqueness in services and products

    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
    eut
    -0.07
    isd
    -0.07
    ality
    -0.07
    ç§
    -0.07
    anus
    -0.06
    alet
    -0.06
    sem
    -0.06
    æĻĤ代
    -0.06
     yeterli
    -0.06
    алÑİ
    -0.06
    POSITIVE LOGITS
    ably
    0.10
    ingly
    0.09
    ocal
    0.07
    stdClass
    0.07
     dedication
    0.07
    ertain
    0.06
     opportunities
    0.06
    errupted
    0.06
     among
    0.06
    able
    0.06
    Activations Density 0.005%

    No Known Activations