© 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. 82155
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes and judicial roles

    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
    714
    -0.06
    estr
    -0.06
    jer
    -0.06
    criptors
    -0.06
     coaching
    -0.06
    ood
    -0.05
     gall
    -0.05
    engo
    -0.05
     norge
    -0.05
     prosecuting
    -0.05
    POSITIVE LOGITS
     except
    0.08
    ads
    0.08
    erif
    0.07
    except
    0.07
    _except
    0.07
    ãĥ³ãĥij
    0.07
    issor
    0.07
    limited
    0.07
     exclusive
    0.07
     limited
    0.07
    Activations Density 0.005%

    No Known Activations