© 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. 129231
    Prev
    Next
    INDEX
    Explanations

    phrases that express strong statements or opinions

    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
    еÑĨ
    -0.06
    /loader
    -0.06
    iset
    -0.06
    ëģĶ
    -0.06
    adata
    -0.06
    rene
    -0.06
    etz
    -0.06
    ellen
    -0.05
     ALERT
    -0.05
    idot
    -0.05
    POSITIVE LOGITS
    ieve
    0.07
    å·Ŀ
    0.07
    xis
    0.06
    pel
    0.06
     âĻ
    0.06
    oke
    0.06
    ogi
    0.06
     Maul
    0.06
    esk
    0.06
    igua
    0.06
    Activations Density 0.028%

    No Known Activations