© 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. 119855
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences and emotional expressions

    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
    iens
    -0.07
    ithe
    -0.07
     unw
    -0.07
    amedi
    -0.06
    uckle
    -0.06
    inen
    -0.06
    arge
    -0.06
    annes
    -0.06
     먼ìłĢ
    -0.06
    avana
    -0.06
    POSITIVE LOGITS
     later
    0.11
     subsequent
    0.10
     subsequently
    0.10
    later
    0.09
    ä¹ĭåIJİ
    0.09
     soon
    0.08
     eventually
    0.08
     Later
    0.08
     thereafter
    0.07
     then
    0.07
    Activations Density 0.040%

    No Known Activations