© 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. 125619
    Prev
    Next
    INDEX
    Explanations

    references to digital media consumption and screen time

    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
     vic
    -0.07
    omm
    -0.07
    rary
    -0.07
    .isUser
    -0.06
    oser
    -0.06
    99
    -0.06
     cel
    -0.06
    shadow
    -0.06
    ourn
    -0.06
    our
    -0.06
    POSITIVE LOGITS
    uye
    0.07
    ollah
    0.07
    ivant
    0.07
    hra
    0.07
    YNC
    0.06
    aad
    0.06
    ysz
    0.06
    NIC
    0.06
    -neutral
    0.06
    istrov
    0.06
    Activations Density 0.023%

    No Known Activations