© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128578
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes and patents

    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
    zier
    -0.08
    loquent
    -0.07
    bots
    -0.06
    ÛĮÙĦ
    -0.06
     Guar
    -0.06
    resi
    -0.06
    /modal
    -0.06
    rans
    -0.06
    oš
    -0.06
    MATRIX
    -0.06
    POSITIVE LOGITS
    ivas
    0.07
    _DETECT
    0.07
     Nature
    0.06
    YPE
    0.06
     human
    0.06
     patent
    0.06
    ponse
    0.06
     natural
    0.06
    RIX
    0.06
    ivos
    0.06
    Activations Density 0.001%

    No Known Activations