© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 59568
    Prev
    Next
    INDEX
    Explanations

    phrases conveying emotional connections and personal memories

    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
    ujet
    -0.08
    izu
    -0.08
    emas
    -0.08
    izona
    -0.07
    ÃŃculo
    -0.07
    usable
    -0.07
    ivate
    -0.07
    ίνη
    -0.07
    chwitz
    -0.07
    IRO
    -0.07
    POSITIVE LOGITS
     pall
    0.07
     trib
    0.07
     loss
    0.06
    iani
    0.06
    or
    0.06
     WE
    0.06
     characteristic
    0.06
    num
    0.06
     PR
    0.05
     precedence
    0.05
    Activations Density 0.010%

    No Known Activations