© 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. 73167
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to AWS SDK and IAM

    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
    um
    -0.06
    ones
    -0.06
    nda
    -0.06
    place
    -0.06
    olo
    -0.06
    stro
    -0.05
    HL
    -0.05
     institution
    -0.05
    con
    -0.05
    ñ
    -0.05
    POSITIVE LOGITS
    ạ
    0.08
    adier
    0.08
     jadx
    0.08
    itm
    0.08
    ledo
    0.07
    æº
    0.07
    .SizeType
    0.07
    олÑİ
    0.07
    nova
    0.07
    .scalablytyped
    0.07
    Activations Density 0.002%

    No Known Activations