© 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 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. 61034
    Prev
    Next
    INDEX
    Explanations

    key terms related to health and necessity in various contexts

    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
    759
    -0.07
    olis
    -0.07
    adi
    -0.07
    ColumnInfo
    -0.06
     Stein
    -0.06
    .CO
    -0.06
    cion
    -0.06
    ulus
    -0.06
     Sheldon
    -0.06
    aroo
    -0.06
    POSITIVE LOGITS
    wit
    0.07
    ãĢģé«ĺ
    0.07
     difficult
    0.07
    éĸĢ
    0.07
     boÄŁ
    0.06
     difÃŃcil
    0.06
    ones
    0.06
     difficulty
    0.06
     elusive
    0.06
     rarity
    0.06
    Activations Density 0.060%

    No Known Activations