© 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 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. 17-LLAMASCOPE-RES-131K
    11. 106606
    Prev
    Next
    INDEX
    Explanations

    phrases related to media coverage and discussion surrounding events

    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
    agn
    -0.08
    itian
    -0.07
    sko
    -0.06
    ali
    -0.06
    alian
    -0.06
    lya
    -0.06
    irs
    -0.06
    agini
    -0.06
    reen
    -0.05
    sic
    -0.05
    POSITIVE LOGITS
     lately
    0.12
     recently
    0.08
    recent
    0.08
    овоÑĢ
    0.07
     pub
    0.07
    ClassNotFoundException
    0.07
    Recently
    0.07
    Focus
    0.07
     devoted
    0.07
     WHETHER
    0.07
    Activations Density 0.029%

    No Known Activations