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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 128693
    Prev
    Next
    INDEX
    Explanations

    terms related to wireless technology and security features

    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
    EDI
    -0.07
    /embed
    -0.06
    æľĿ
    -0.06
     griev
    -0.06
    æĴ
    -0.06
     Mach
    -0.06
    uments
    -0.06
     double
    -0.06
    xed
    -0.06
    WND
    -0.06
    POSITIVE LOGITS
     pairing
    0.08
     Indoor
    0.07
     Pair
    0.07
    .pair
    0.07
     indoor
    0.07
    alth
    0.06
    	TokenName
    0.06
     iTunes
    0.06
     Manuals
    0.06
    actory
    0.06
    Activations Density 0.008%

    No Known Activations