© 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. 94292
    Prev
    Next
    INDEX
    Explanations

    terms related to spam and email filtering

    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
    ally
    -0.08
    s
    -0.07
    aal
    -0.07
    aft
    -0.07
    unes
    -0.06
    /current
    -0.06
    .
    -0.06
    a
    -0.06
    hod
    -0.06
    (s
    -0.06
    POSITIVE LOGITS
    ming
    0.09
    еÑĢп
    0.08
    vertisement
    0.08
    ishly
    0.08
    nesty
    0.07
    cılar
    0.07
    roulette
    0.07
    ulence
    0.07
    ouflage
    0.07
    dex
    0.07
    Activations Density 0.005%

    No Known Activations