© 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. 79371
    Prev
    Next
    INDEX
    Explanations

    mentions of CNN as a news outlet

    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
    bred
    -0.08
    amba
    -0.07
    urovision
    -0.06
    rowsable
    -0.06
    िण
    -0.06
     Redistribution
    -0.06
    ater
    -0.06
    ä½ĵ
    -0.06
    aterno
    -0.06
    JECT
    -0.06
    POSITIVE LOGITS
     shame
    0.07
    issance
    0.07
    yan
    0.07
    fy
    0.07
    -US
    0.07
    ye
    0.07
    izr
    0.07
     Uns
    0.07
    arti
    0.07
    bersome
    0.07
    Activations Density 0.003%

    No Known Activations