© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126908
    Prev
    Next
    INDEX
    Explanations

    significant mentions of news organizations

    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
    åĬ¨çĶŁæĪIJ
    -0.07
    eteor
    -0.07
    519
    -0.07
    alam
    -0.06
    uant
    -0.06
    pecified
    -0.06
    urovision
    -0.06
    omics
    -0.06
    etting
    -0.06
     onCancelled
    -0.06
    POSITIVE LOGITS
    chos
    0.08
     screen
    0.06
    esian
    0.06
    screen
    0.06
    abant
    0.06
    itia
    0.06
    criteria
    0.06
     Lid
    0.06
    NullOr
    0.06
     Mits
    0.06
    Activations Density 0.000%

    No Known Activations