© 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. 105452
    Prev
    Next
    INDEX
    Explanations

    elements related to legends and symbolism

    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
    ffen
    -0.07
    wald
    -0.07
    ç¸
    -0.07
    ruz
    -0.07
    çĽ
    -0.07
    ais
    -0.07
    serrat
    -0.07
    amins
    -0.06
    aign
    -0.06
    ertainment
    -0.06
    POSITIVE LOGITS
    @Web
    0.07
    ine
    0.06
     Sly
    0.06
    åĽ½ãģ®
    0.06
     forever
    0.06
    conte
    0.06
     became
    0.06
    ject
    0.05
     Pett
    0.05
     صÙĦÙī
    0.05
    Activations Density 0.007%

    No Known Activations