Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125736
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental hazards and regulatory actions

    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
    weise
    -0.07
     maç
    -0.06
    CTX
    -0.06
    RICS
    -0.06
    .Ui
    -0.06
    'gc
    -0.06
     kennenlernen
    -0.06
    VEL
    -0.06
    æı
    -0.06
    reno
    -0.06
    POSITIVE LOGITS
     spill
    0.14
     leaked
    0.12
     spilled
    0.12
     leak
    0.12
     spills
    0.12
     leaks
    0.11
     leakage
    0.10
     leaking
    0.10
     Leakage
    0.09
     Leak
    0.09
    Activations Density 0.112%

    No Known Activations