© 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. 127426
    Prev
    Next
    INDEX
    Explanations

    terms related to judicial and rehabilitation processes

    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
     (
    -0.06
    olk
    -0.06
    -0.06
    .Management
    -0.06
     Alabama
    -0.06
     Love
    -0.05
     statewide
    -0.05
     Pist
    -0.05
     using
    -0.05
     "
    -0.05
    POSITIVE LOGITS
    xce
    0.08
    YTE
    0.08
    )prepare
    0.08
    setVisibility
    0.07
    _GAP
    0.07
    }elseif
    0.07
    rap
    0.07
     spoilers
    0.07
    frica
    0.07
    Prostit
    0.07
    Activations Density 0.001%

    No Known Activations