© 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. 40466
    Prev
    Next
    INDEX
    Explanations

    terms related to weight measurement and physical injuries

    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
    ponent
    -0.08
    Ùĩ
    -0.07
    brew
    -0.07
    conde
    -0.07
    quired
    -0.07
    BERS
    -0.07
    berra
    -0.07
    ÑģÑĭ
    -0.07
    embros
    -0.07
    otas
    -0.07
    POSITIVE LOGITS
    ings
    0.12
    edly
    0.09
    mass
    0.08
    ร
    0.08
    ship
    0.08
    ers
    0.08
    ÂŃing
    0.07
    nut
    0.07
    ré
    0.07
    ishments
    0.07
    Activations Density 0.030%

    No Known Activations