© 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. 15-LLAMASCOPE-RES-131K
    11. 87857
    Prev
    Next
    INDEX
    Explanations

    expressions related to pain and its severity

    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
    gether
    -0.08
    edia
    -0.08
    bildung
    -0.07
    jev
    -0.07
    ecs
    -0.07
    خاÙĨÙĩ
    -0.07
    ization
    -0.07
    -wide
    -0.07
    iate
    -0.07
    uted
    -0.06
    POSITIVE LOGITS
    lessly
    0.10
    fully
    0.09
    kill
    0.09
    killer
    0.08
    /problems
    0.07
    staking
    0.07
    far
    0.07
    gren
    0.07
    tm
    0.07
    ful
    0.07
    Activations Density 0.010%

    No Known Activations