© 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. 17-LLAMASCOPE-RES-131K
    11. 61435
    Prev
    Next
    INDEX
    Explanations

    concepts related to humiliation and self-deprecation

    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
    ekli
    -0.07
     khúc
    -0.07
    hte
    -0.07
    arme
    -0.07
     ì§ĢëĤľ
    -0.06
     outnumber
    -0.06
     unpopular
    -0.06
    achi
    -0.06
    ANC
    -0.06
    pawn
    -0.06
    POSITIVE LOGITS
     Guys
    0.06
    CLR
    0.06
    iband
    0.06
     ward
    0.06
    lessness
    0.06
    ä¼ģ
    0.06
    imentary
    0.06
    åĨĬ
    0.06
     horizon
    0.06
    éric
    0.06
    Activations Density 0.000%

    No Known Activations