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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 74992
    Prev
    Next
    INDEX
    Explanations

    expressions of longing or missing someone

    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
    onium
    -0.07
    ?q
    -0.07
    éľĩ
    -0.06
    erator
    -0.06
    emp
    -0.06
    oltip
    -0.06
     Gors
    -0.06
    ephir
    -0.06
     tá»Ń
    -0.06
     законом
    -0.06
    POSITIVE LOGITS
    Missing
    0.08
    miss
    0.08
     missed
    0.08
     misses
    0.08
     missing
    0.08
     miss
    0.08
    rost
    0.08
     longing
    0.07
    missing
    0.07
     absence
    0.07
    Activations Density 0.028%

    No Known Activations