© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 124805
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and 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
    DOI
    -0.07
    ihat
    -0.07
    rgb
    -0.07
    ucer
    -0.06
     âŁ
    -0.06
    qid
    -0.06
    redient
    -0.06
     اÙĦÙĨÙĪ
    -0.06
    VID
    -0.06
    534
    -0.06
    POSITIVE LOGITS
    fault
    0.07
     vegetarian
    0.06
    nech
    0.06
    ifer
    0.06
    Äįe
    0.06
     Uncategorized
    0.06
    ιÏİν
    0.06
    .localization
    0.06
    gfx
    0.06
     Santana
    0.06
    Activations Density 0.002%

    No Known Activations