© 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 EvalsExportsinterp-engineNEWAPI 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. 105224
    Prev
    Next
    INDEX
    Explanations

    discussions around safety and health-related concerns

    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
     Prescription
    -0.07
    ê°IJ
    -0.06
    613
    -0.06
     bufsize
    -0.06
    IRD
    -0.06
    spo
    -0.06
    otti
    -0.06
     ow
    -0.06
     valu
    -0.05
    اخت
    -0.05
    POSITIVE LOGITS
     safe
    0.16
     safety
    0.16
    safe
    0.14
     Safe
    0.14
     Safety
    0.14
    -safe
    0.13
    Safe
    0.13
     safer
    0.13
    Safety
    0.13
     safely
    0.13
    Activations Density 0.065%

    No Known Activations