© 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. 41123
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate terms related to legal or patent language

    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
    agn
    -0.06
    qu
    -0.06
     ‘
    -0.06
    ker
    -0.06
     –
    -0.06
     поба
    -0.06
     Schn
    -0.06
    228
    -0.06
    agg
    -0.05
    vs
    -0.05
    POSITIVE LOGITS
    CLUDED
    0.08
    hek
    0.08
    avatel
    0.08
    opup
    0.08
    aģın
    0.07
    klad
    0.07
    IJ
    0.07
    ária
    0.07
    аÑĤкÑĥ
    0.07
    å±±å¸Ĥ
    0.07
    Activations Density 0.000%

    No Known Activations