© 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. 2689
    Prev
    Next
    INDEX
    Explanations

    references to legal or official documents and processes

    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
    ioso
    -0.07
    anner
    -0.06
    Spoiler
    -0.06
    ÑĥÑĩаÑģ
    -0.06
    .scalablytyped
    -0.06
    elib
    -0.06
    DidLoad
    -0.06
    elo
    -0.06
    _lazy
    -0.06
     san
    -0.06
    POSITIVE LOGITS
    ieber
    0.07
     Signature
    0.07
    _signature
    0.07
    ếp
    0.07
     signatures
    0.06
     signature
    0.06
    inski
    0.06
    amon
    0.06
    çĴ
    0.06
    inue
    0.06
    Activations Density 0.007%

    No Known Activations