© 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. 106261
    Prev
    Next
    INDEX
    Explanations

    expressions related to goal setting or ambitions

    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
     verr
    -0.06
    onte
    -0.06
     molto
    -0.06
    éĢĤ
    -0.06
     Laud
    -0.06
    دÙĪد
    -0.06
     pronto
    -0.06
    ign
    -0.06
     plenty
    -0.06
    uitar
    -0.06
    POSITIVE LOGITS
    å¦ĤæѤ
    0.07
     à¤ĩतन
    0.07
    mere
    0.07
     ìĻĶ
    0.06
     ìĿ´ëłĩê²Į
    0.06
     ìŀĪëĭ¤ëĬĶ
    0.06
    utters
    0.06
    ynos
    0.06
    landscape
    0.06
    iest
    0.06
    Activations Density 0.021%

    No Known Activations