© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75286
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jonas" and its variations in different 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
    agos
    -0.08
    ÙħاÙĨÛĮ
    -0.07
    urus
    -0.07
    aret
    -0.07
    ablish
    -0.07
    oga
    -0.07
    awah
    -0.06
    orgen
    -0.06
    ernet
    -0.06
    608
    -0.06
    POSITIVE LOGITS
    athon
    0.09
     Ive
    0.07
    oth
    0.06
    shima
    0.06
    cant
    0.06
    ypad
    0.06
    tero
    0.06
    cu
    0.06
    UTTON
    0.06
    YS
    0.06
    Activations Density 0.011%

    No Known Activations