© 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. 89164
    Prev
    Next
    INDEX
    Explanations

    expressions indicating nostalgia or reminiscence

    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
    ä¼¼
    -0.07
     eldre
    -0.07
     embry
    -0.07
    à¹Īà¸Ńà¹Ħà¸Ľ
    -0.06
    juven
    -0.06
    åĪļæīį
    -0.06
    isplay
    -0.06
    à¥įयत
    -0.06
    ropdown
    -0.06
    upal
    -0.06
    POSITIVE LOGITS
    pis
    0.07
    Mailer
    0.07
    ucker
    0.06
    eneration
    0.06
    ÃŃny
    0.06
     Bonus
    0.06
    象
    0.06
    ija
    0.06
     Rom
    0.06
    err
    0.06
    Activations Density 0.000%

    No Known Activations