© 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. 9-LLAMASCOPE-RES-131K
    11. 98139
    Prev
    Next
    INDEX
    Explanations

    terms related to accountability and liability in a legal context

    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
    éĺħ读次æķ°
    -0.07
     Dün
    -0.07
     INDIRECT
    -0.06
    Å©i
    -0.06
    adlo
    -0.06
     Kraj
    -0.06
    Assertions
    -0.06
    ailed
    -0.06
    arg
    -0.06
    Prostit
    -0.06
    POSITIVE LOGITS
     Manuals
    0.06
    ersist
    0.06
    itech
    0.06
    sdk
    0.06
    razier
    0.06
    itar
    0.06
    VERS
    0.06
    íķ´
    0.05
     SPDX
    0.05
     Bias
    0.05
    Activations Density 0.002%

    No Known Activations