© 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 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. 56139
    Prev
    Next
    INDEX
    Explanations

    phrases that express strong emotions or conditions related to interpersonal relationships

    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
     sez
    -0.10
     kred
    -0.10
    бÑĥдÑĮ
    -0.10
    ceae
    -0.10
    ÑģÑĤÑİ
    -0.09
    anter
    -0.09
    кол
    -0.09
    -Semit
    -0.09
    ignet
    -0.09
    olumn
    -0.09
    POSITIVE LOGITS
    âĢ¦↵
    0.07
     âĢ¦↵
    0.07
     “
    0.06
     âģ
    0.06
     attempt
    0.06
     foregoing
    0.05
     exclusively
    0.05
     whilst
    0.05
    0.05
     budding
    0.05
    Activations Density 0.002%

    No Known Activations