© 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. 41352
    Prev
    Next
    INDEX
    Explanations

    technical terms related to structured data formats

    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
    jug
    -0.06
    ez
    -0.06
     Bridge
    -0.06
    phylum
    -0.06
    arp
    -0.06
    sortable
    -0.05
     Sle
    -0.05
    orate
    -0.05
    669
    -0.05
    sy
    -0.05
    POSITIVE LOGITS
    ÌĨ
    0.09
    IfExists
    0.07
    isto
    0.07
    ANDLE
    0.07
    iston
    0.07
    urator
    0.07
    eson
    0.06
    LOOR
    0.06
    Hint
    0.06
    Qualifier
    0.06
    Activations Density 0.000%

    No Known Activations