© 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. 83649
    Prev
    Next
    INDEX
    Explanations

    feelings of uncertainty and change associated with personal growth and relationships

    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
     kami
    -0.08
     tonight
    -0.07
    okes
    -0.07
    etyl
    -0.07
     telah
    -0.07
    iliz
    -0.07
    agna
    -0.06
    ÏħÏĩ
    -0.06
     now
    -0.06
     myself
    -0.06
    POSITIVE LOGITS
     yourself
    0.13
     oneself
    0.13
     your
    0.09
    your
    0.09
    ä½łçļĦ
    0.09
     becomes
    0.08
     yourselves
    0.08
    ä½ł
    0.08
     you
    0.08
     youre
    0.07
    Activations Density 0.255%

    No Known Activations