© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128480
    Prev
    Next
    INDEX
    Explanations

    instances of login-related actions or prompts

    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
       
    -0.06
     Sith
    -0.06
    walker
    -0.06
      
    -0.06
     opposite
    -0.06
     somebody
    -0.06
     bel
    -0.06
    placeholders
    -0.06
     setups
    -0.06
    webtoken
    -0.06
    POSITIVE LOGITS
    avian
    0.07
     manoe
    0.07
    ULA
    0.06
    isz
    0.06
    éĿ©åij½
    0.06
    ajas
    0.06
    adan
    0.06
    quan
    0.06
    asd
    0.06
    elm
    0.06
    Activations Density 0.000%

    No Known Activations