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

    Neuronpedia

    Jacobian LensNEW
    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. 85969
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential risks or conditions that may have serious implications

    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
    aeda
    -0.07
    аÑĢÑĮ
    -0.07
     extrem
    -0.07
    upertino
    -0.07
    ksam
    -0.06
    dden
    -0.06
    crud
    -0.06
     Conditional
    -0.06
    ÌĨ
    -0.06
     Eisen
    -0.06
    POSITIVE LOGITS
     Tape
    0.06
    kre
    0.06
    je
    0.06
     akci
    0.06
    agen
    0.05
    ùi
    0.05
    ulo
    0.05
    ilden
    0.05
    igan
    0.05
    oppers
    0.05
    Activations Density 0.006%

    No Known Activations