© 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. 128914
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions and group dynamics

    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
     various
    -0.07
    esseract
    -0.07
    LEASE
    -0.06
    ãĥĥãĤ°
    -0.06
    cola
    -0.06
    -0.06
     NÄĽm
    -0.06
    ifle
    -0.06
     Simone
    -0.06
    inning
    -0.06
    POSITIVE LOGITS
    -Compatible
    0.07
    282
    0.07
     tonight
    0.07
     tomorrow
    0.06
    827
    0.06
    jsc
    0.06
    <?↵
    0.06
    /unit
    0.06
    877
    0.06
    Callbacks
    0.06
    Activations Density 0.094%

    No Known Activations