© 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. 15-LLAMASCOPE-RES-131K
    11. 89777
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions and reactions

    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
     Fucked
    -0.07
    empo
    -0.07
    çł
    -0.07
    ÑģÑĤаÑĤи
    -0.07
    ابر
    -0.07
    ildo
    -0.07
    ĶåĽŀ
    -0.07
    loom
    -0.07
    .ReadString
    -0.07
    EX
    -0.07
    POSITIVE LOGITS
     Wake
    0.06
    sad
    0.06
    estination
    0.06
    ulet
    0.06
    werk
    0.06
     Sad
    0.05
     Sabb
    0.05
     Drop
    0.05
    éĢļ
    0.05
    å©
    0.05
    Activations Density 0.023%

    No Known Activations