© 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. 30323
    Prev
    Next
    INDEX
    Explanations

    mentions of classifications and ratings related to levels or degrees of severity

    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
    boom
    -0.06
    exampleInputEmail
    -0.06
     Statistics
    -0.06
    lists
    -0.06
    orse
    -0.06
    agers
    -0.06
    plat
    -0.05
     Records
    -0.05
     Marketable
    -0.05
    askell
    -0.05
    POSITIVE LOGITS
     level
    0.13
     Level
    0.12
     rating
    0.12
    Level
    0.10
    level
    0.10
     LEVEL
    0.10
     levels
    0.10
    _level
    0.10
    LEVEL
    0.10
    -rating
    0.10
    Activations Density 0.072%

    No Known Activations