© 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. 117965
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with announcements and public communication regarding personal struggles or battles

    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
    ucken
    -0.07
    /Core
    -0.07
    ¶Į
    -0.07
    ÙĦات
    -0.06
    ãģĦãģĭ
    -0.06
    ÙĦت
    -0.06
    bara
    -0.06
    aland
    -0.06
    å±±å¸Ĥ
    -0.06
    cores
    -0.06
    POSITIVE LOGITS
    aged
    0.07
    yst
    0.07
    quit
    0.07
     quits
    0.06
     via
    0.06
     plans
    0.06
     departure
    0.06
     Garr
    0.06
     BIT
    0.06
    èĦ
    0.06
    Activations Density 0.010%

    No Known Activations