© 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. 108012
    Prev
    Next
    INDEX
    Explanations

    expressions of nostalgia and related sentiments

    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
    manship
    -0.08
    igham
    -0.07
    alet
    -0.07
    eko
    -0.07
    rices
    -0.07
    åĪ¶
    -0.06
    arl
    -0.06
    hattan
    -0.06
    ets
    -0.06
    ings
    -0.06
    POSITIVE LOGITS
    uet
    0.07
    gression
    0.07
    ĶåĽŀ
    0.07
    ionales
    0.07
    ksi
    0.07
    /back
    0.07
    .googleapis
    0.07
    ichel
    0.07
    irm
    0.07
    gressive
    0.07
    Activations Density 0.004%

    No Known Activations