© 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. 17-LLAMASCOPE-RES-131K
    11. 70494
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and conditions

    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
     Tib
    -0.06
    íĥĦ
    -0.06
    poke
    -0.06
    .moves
    -0.06
    _lite
    -0.06
    cred
    -0.06
    วà¸Ļ
    -0.06
    wine
    -0.06
     cob
    -0.05
    ugen
    -0.05
    POSITIVE LOGITS
     MERCHANTABILITY
    0.07
    ibaba
    0.07
    èħIJ
    0.07
    boro
    0.06
    thouse
    0.06
    _SECURE
    0.06
    HELL
    0.06
     Trace
    0.06
    ::__
    0.06
    umph
    0.06
    Activations Density 0.001%

    No Known Activations