© 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. 129488
    Prev
    Next
    INDEX
    Explanations

    positive affirmations regarding conditions or instructions

    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
    must
    -0.06
    CISION
    -0.06
     Tire
    -0.06
    å¿ħé¡»
    -0.06
    onis
    -0.06
     å¿ħ
    -0.06
    ]|[
    -0.06
    ald
    -0.06
     ãĥĶ
    -0.06
    аÑĢÑı
    -0.06
    POSITIVE LOGITS
     OK
    0.10
     safe
    0.10
    OK
    0.09
     okay
    0.09
    safe
    0.09
    -safe
    0.08
     ok
    0.08
     Safe
    0.08
     safely
    0.08
     proceed
    0.08
    Activations Density 0.035%

    No Known Activations