© 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. 77188
    Prev
    Next
    INDEX
    Explanations

    references to American products and services

    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
    agini
    -0.06
    yre
    -0.05
    å¤ķ
    -0.05
    Bloc
    -0.05
     Marilyn
    -0.05
     Moor
    -0.05
     Booth
    -0.05
     Pav
    -0.05
     Burr
    -0.05
     v
    -0.05
    POSITIVE LOGITS
    obel
    0.08
    alom
    0.08
    _Base
    0.08
    /Base
    0.08
    TabPage
    0.08
    compound
    0.08
    ethyst
    0.07
     exp
    0.07
     Base
    0.07
     compounds
    0.07
    Activations Density 0.081%

    No Known Activations